summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm
diff options
context:
space:
mode:
authorAnton Arapov <anton@redhat.com>2012-06-08 12:58:00 +0200
committerAnton Arapov <anton@redhat.com>2012-06-08 12:58:00 +0200
commit6792a3f47a2e42d7164292bf7f1a55cfc4c91652 (patch)
treeb90c002bfbbeaec92f5d8a2383dcabf6524016f7 /arch/x86/include/asm
parentfe2895d3d55146cac65b273c0f83e2c7e543cd0e (diff)
downloadkernel-uprobes-6792a3f47a2e42d7164292bf7f1a55cfc4c91652.tar.gz
kernel-uprobes-6792a3f47a2e42d7164292bf7f1a55cfc4c91652.tar.xz
kernel-uprobes-6792a3f47a2e42d7164292bf7f1a55cfc4c91652.zip
fedora kernel: b920e9b748c595f970bf80ede7832d39f8d567dav3.4.1-2
Signed-off-by: Anton Arapov <anton@redhat.com>
Diffstat (limited to 'arch/x86/include/asm')
-rw-r--r--arch/x86/include/asm/Kbuild2
-rw-r--r--arch/x86/include/asm/alternative.h6
-rw-r--r--arch/x86/include/asm/apic.h7
-rw-r--r--arch/x86/include/asm/atomic64_32.h146
-rw-r--r--arch/x86/include/asm/auxvec.h7
-rw-r--r--arch/x86/include/asm/barrier.h116
-rw-r--r--arch/x86/include/asm/bug.h4
-rw-r--r--arch/x86/include/asm/cacheflush.h1
-rw-r--r--arch/x86/include/asm/compat.h40
-rw-r--r--arch/x86/include/asm/cpu_device_id.h13
-rw-r--r--arch/x86/include/asm/cpufeature.h4
-rw-r--r--arch/x86/include/asm/debugreg.h67
-rw-r--r--arch/x86/include/asm/desc.h25
-rw-r--r--arch/x86/include/asm/dma-mapping.h26
-rw-r--r--arch/x86/include/asm/efi.h2
-rw-r--r--arch/x86/include/asm/elf.h32
-rw-r--r--arch/x86/include/asm/exec.h1
-rw-r--r--arch/x86/include/asm/fpu-internal.h520
-rw-r--r--arch/x86/include/asm/futex.h1
-rw-r--r--arch/x86/include/asm/hardirq.h1
-rw-r--r--arch/x86/include/asm/highmem.h2
-rw-r--r--arch/x86/include/asm/i387.h589
-rw-r--r--arch/x86/include/asm/ia32.h18
-rw-r--r--arch/x86/include/asm/idle.h1
-rw-r--r--arch/x86/include/asm/inat.h5
-rw-r--r--arch/x86/include/asm/insn.h18
-rw-r--r--arch/x86/include/asm/io_apic.h40
-rw-r--r--arch/x86/include/asm/irq_controller.h12
-rw-r--r--arch/x86/include/asm/jump_label.h6
-rw-r--r--arch/x86/include/asm/kgdb.h10
-rw-r--r--arch/x86/include/asm/kvm.h4
-rw-r--r--arch/x86/include/asm/kvm_emulate.h3
-rw-r--r--arch/x86/include/asm/kvm_host.h63
-rw-r--r--arch/x86/include/asm/kvm_para.h3
-rw-r--r--arch/x86/include/asm/local.h1
-rw-r--r--arch/x86/include/asm/mc146818rtc.h1
-rw-r--r--arch/x86/include/asm/mce.h2
-rw-r--r--arch/x86/include/asm/mmu.h8
-rw-r--r--arch/x86/include/asm/mrst.h4
-rw-r--r--arch/x86/include/asm/msr-index.h7
-rw-r--r--arch/x86/include/asm/mtrr.h28
-rw-r--r--arch/x86/include/asm/page_types.h1
-rw-r--r--arch/x86/include/asm/paravirt.h13
-rw-r--r--arch/x86/include/asm/paravirt_types.h3
-rw-r--r--arch/x86/include/asm/perf_event.h3
-rw-r--r--arch/x86/include/asm/pgtable-3level.h50
-rw-r--r--arch/x86/include/asm/posix_types.h2
-rw-r--r--arch/x86/include/asm/posix_types_32.h75
-rw-r--r--arch/x86/include/asm/posix_types_64.h106
-rw-r--r--arch/x86/include/asm/posix_types_x32.h19
-rw-r--r--arch/x86/include/asm/processor.h97
-rw-r--r--arch/x86/include/asm/prom.h10
-rw-r--r--arch/x86/include/asm/ptrace.h1
-rw-r--r--arch/x86/include/asm/segment.h58
-rw-r--r--arch/x86/include/asm/sigcontext.h57
-rw-r--r--arch/x86/include/asm/sigframe.h13
-rw-r--r--arch/x86/include/asm/sighandling.h24
-rw-r--r--arch/x86/include/asm/siginfo.h8
-rw-r--r--arch/x86/include/asm/special_insns.h199
-rw-r--r--arch/x86/include/asm/spinlock.h4
-rw-r--r--arch/x86/include/asm/spinlock_types.h1
-rw-r--r--arch/x86/include/asm/stackprotector.h1
-rw-r--r--arch/x86/include/asm/switch_to.h129
-rw-r--r--arch/x86/include/asm/sys_ia32.h7
-rw-r--r--arch/x86/include/asm/syscall.h5
-rw-r--r--arch/x86/include/asm/system.h523
-rw-r--r--arch/x86/include/asm/thread_info.h18
-rw-r--r--arch/x86/include/asm/tlbflush.h2
-rw-r--r--arch/x86/include/asm/traps.h25
-rw-r--r--arch/x86/include/asm/tsc.h4
-rw-r--r--arch/x86/include/asm/uaccess.h2
-rw-r--r--arch/x86/include/asm/uaccess_32.h5
-rw-r--r--arch/x86/include/asm/uaccess_64.h4
-rw-r--r--arch/x86/include/asm/unistd.h13
-rw-r--r--arch/x86/include/asm/vga.h2
-rw-r--r--arch/x86/include/asm/vgtod.h17
-rw-r--r--arch/x86/include/asm/virtext.h1
-rw-r--r--arch/x86/include/asm/word-at-a-time.h79
-rw-r--r--arch/x86/include/asm/x2apic.h5
-rw-r--r--arch/x86/include/asm/x86_init.h14
-rw-r--r--arch/x86/include/asm/xen/interface.h1
81 files changed, 1799 insertions, 1648 deletions
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index b57e6a43a37..f9c0d3ba9e8 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -14,6 +14,7 @@ header-y += msr.h
header-y += mtrr.h
header-y += posix_types_32.h
header-y += posix_types_64.h
+header-y += posix_types_x32.h
header-y += prctl.h
header-y += processor-flags.h
header-y += ptrace-abi.h
@@ -24,3 +25,4 @@ header-y += vsyscall.h
genhdr-y += unistd_32.h
genhdr-y += unistd_64.h
+genhdr-y += unistd_x32.h
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 37ad100a221..49331bedc15 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -145,6 +145,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
*/
#define ASM_OUTPUT2(a...) a
+/*
+ * use this macro if you need clobbers but no inputs in
+ * alternative_{input,io,call}()
+ */
+#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
+
struct paravirt_patch_site;
#ifdef CONFIG_PARAVIRT
void apply_paravirt(struct paravirt_patch_site *start,
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 3ab9bdd87e7..d8541017126 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -11,7 +11,6 @@
#include <linux/atomic.h>
#include <asm/fixmap.h>
#include <asm/mpspec.h>
-#include <asm/system.h>
#include <asm/msr.h>
#define ARCH_APICTIMER_STOPS_ON_C3 1
@@ -288,6 +287,7 @@ struct apic {
int (*probe)(void);
int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
+ int (*apic_id_valid)(int apicid);
int (*apic_id_registered)(void);
u32 irq_delivery_mode;
@@ -532,6 +532,11 @@ static inline unsigned int read_apic_id(void)
return apic->get_apic_id(reg);
}
+static inline int default_apic_id_valid(int apicid)
+{
+ return (apicid < 255);
+}
+
extern void default_setup_apic_routing(void);
extern struct apic apic_noop;
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index fa13f0ec287..198119910da 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -14,13 +14,52 @@ typedef struct {
#define ATOMIC64_INIT(val) { (val) }
+#define __ATOMIC64_DECL(sym) void atomic64_##sym(atomic64_t *, ...)
+#ifndef ATOMIC64_EXPORT
+#define ATOMIC64_DECL_ONE __ATOMIC64_DECL
+#else
+#define ATOMIC64_DECL_ONE(sym) __ATOMIC64_DECL(sym); \
+ ATOMIC64_EXPORT(atomic64_##sym)
+#endif
+
#ifdef CONFIG_X86_CMPXCHG64
-#define ATOMIC64_ALTERNATIVE_(f, g) "call atomic64_" #g "_cx8"
+#define __alternative_atomic64(f, g, out, in...) \
+ asm volatile("call %P[func]" \
+ : out : [func] "i" (atomic64_##g##_cx8), ## in)
+
+#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
#else
-#define ATOMIC64_ALTERNATIVE_(f, g) ALTERNATIVE("call atomic64_" #f "_386", "call atomic64_" #g "_cx8", X86_FEATURE_CX8)
+#define __alternative_atomic64(f, g, out, in...) \
+ alternative_call(atomic64_##f##_386, atomic64_##g##_cx8, \
+ X86_FEATURE_CX8, ASM_OUTPUT2(out), ## in)
+
+#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8); \
+ ATOMIC64_DECL_ONE(sym##_386)
+
+ATOMIC64_DECL_ONE(add_386);
+ATOMIC64_DECL_ONE(sub_386);
+ATOMIC64_DECL_ONE(inc_386);
+ATOMIC64_DECL_ONE(dec_386);
#endif
-#define ATOMIC64_ALTERNATIVE(f) ATOMIC64_ALTERNATIVE_(f, f)
+#define alternative_atomic64(f, out, in...) \
+ __alternative_atomic64(f, f, ASM_OUTPUT2(out), ## in)
+
+ATOMIC64_DECL(read);
+ATOMIC64_DECL(set);
+ATOMIC64_DECL(xchg);
+ATOMIC64_DECL(add_return);
+ATOMIC64_DECL(sub_return);
+ATOMIC64_DECL(inc_return);
+ATOMIC64_DECL(dec_return);
+ATOMIC64_DECL(dec_if_positive);
+ATOMIC64_DECL(inc_not_zero);
+ATOMIC64_DECL(add_unless);
+
+#undef ATOMIC64_DECL
+#undef ATOMIC64_DECL_ONE
+#undef __ATOMIC64_DECL
+#undef ATOMIC64_EXPORT
/**
* atomic64_cmpxchg - cmpxchg atomic64 variable
@@ -50,11 +89,9 @@ static inline long long atomic64_xchg(atomic64_t *v, long long n)
long long o;
unsigned high = (unsigned)(n >> 32);
unsigned low = (unsigned)n;
- asm volatile(ATOMIC64_ALTERNATIVE(xchg)
- : "=A" (o), "+b" (low), "+c" (high)
- : "S" (v)
- : "memory"
- );
+ alternative_atomic64(xchg, "=&A" (o),
+ "S" (v), "b" (low), "c" (high)
+ : "memory");
return o;
}
@@ -69,11 +106,9 @@ static inline void atomic64_set(atomic64_t *v, long long i)
{
unsigned high = (unsigned)(i >> 32);
unsigned low = (unsigned)i;
- asm volatile(ATOMIC64_ALTERNATIVE(set)
- : "+b" (low), "+c" (high)
- : "S" (v)
- : "eax", "edx", "memory"
- );
+ alternative_atomic64(set, /* no output */,
+ "S" (v), "b" (low), "c" (high)
+ : "eax", "edx", "memory");
}
/**
@@ -85,10 +120,7 @@ static inline void atomic64_set(atomic64_t *v, long long i)
static inline long long atomic64_read(const atomic64_t *v)
{
long long r;
- asm volatile(ATOMIC64_ALTERNATIVE(read)
- : "=A" (r), "+c" (v)
- : : "memory"
- );
+ alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
return r;
}
@@ -101,10 +133,9 @@ static inline long long atomic64_read(const atomic64_t *v)
*/
static inline long long atomic64_add_return(long long i, atomic64_t *v)
{
- asm volatile(ATOMIC64_ALTERNATIVE(add_return)
- : "+A" (i), "+c" (v)
- : : "memory"
- );
+ alternative_atomic64(add_return,
+ ASM_OUTPUT2("+A" (i), "+c" (v)),
+ ASM_NO_INPUT_CLOBBER("memory"));
return i;
}
@@ -113,32 +144,25 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v)
*/
static inline long long atomic64_sub_return(long long i, atomic64_t *v)
{
- asm volatile(ATOMIC64_ALTERNATIVE(sub_return)
- : "+A" (i), "+c" (v)
- : : "memory"
- );
+ alternative_atomic64(sub_return,
+ ASM_OUTPUT2("+A" (i), "+c" (v)),
+ ASM_NO_INPUT_CLOBBER("memory"));
return i;
}
static inline long long atomic64_inc_return(atomic64_t *v)
{
long long a;
- asm volatile(ATOMIC64_ALTERNATIVE(inc_return)
- : "=A" (a)
- : "S" (v)
- : "memory", "ecx"
- );
+ alternative_atomic64(inc_return, "=&A" (a),
+ "S" (v) : "memory", "ecx");
return a;
}
static inline long long atomic64_dec_return(atomic64_t *v)
{
long long a;
- asm volatile(ATOMIC64_ALTERNATIVE(dec_return)
- : "=A" (a)
- : "S" (v)
- : "memory", "ecx"
- );
+ alternative_atomic64(dec_return, "=&A" (a),
+ "S" (v) : "memory", "ecx");
return a;
}
@@ -151,10 +175,9 @@ static inline long long atomic64_dec_return(atomic64_t *v)
*/
static inline long long atomic64_add(long long i, atomic64_t *v)
{
- asm volatile(ATOMIC64_ALTERNATIVE_(add, add_return)
- : "+A" (i), "+c" (v)
- : : "memory"
- );
+ __alternative_atomic64(add, add_return,
+ ASM_OUTPUT2("+A" (i), "+c" (v)),
+ ASM_NO_INPUT_CLOBBER("memory"));
return i;
}
@@ -167,10 +190,9 @@ static inline long long atomic64_add(long long i, atomic64_t *v)
*/
static inline long long atomic64_sub(long long i, atomic64_t *v)
{
- asm volatile(ATOMIC64_ALTERNATIVE_(sub, sub_return)
- : "+A" (i), "+c" (v)
- : : "memory"
- );
+ __alternative_atomic64(sub, sub_return,
+ ASM_OUTPUT2("+A" (i), "+c" (v)),
+ ASM_NO_INPUT_CLOBBER("memory"));
return i;
}
@@ -196,10 +218,8 @@ static inline int atomic64_sub_and_test(long long i, atomic64_t *v)
*/
static inline void atomic64_inc(atomic64_t *v)
{
- asm volatile(ATOMIC64_ALTERNATIVE_(inc, inc_return)
- : : "S" (v)
- : "memory", "eax", "ecx", "edx"
- );
+ __alternative_atomic64(inc, inc_return, /* no output */,
+ "S" (v) : "memory", "eax", "ecx", "edx");
}
/**
@@ -210,10 +230,8 @@ static inline void atomic64_inc(atomic64_t *v)
*/
static inline void atomic64_dec(atomic64_t *v)
{
- asm volatile(ATOMIC64_ALTERNATIVE_(dec, dec_return)
- : : "S" (v)
- : "memory", "eax", "ecx", "edx"
- );
+ __alternative_atomic64(dec, dec_return, /* no output */,
+ "S" (v) : "memory", "eax", "ecx", "edx");
}
/**
@@ -263,15 +281,15 @@ static inline int atomic64_add_negative(long long i, atomic64_t *v)
* @u: ...unless v is equal to u.
*
* Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
+ * Returns non-zero if the add was done, zero otherwise.
*/
static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
{
unsigned low = (unsigned)u;
unsigned high = (unsigned)(u >> 32);
- asm volatile(ATOMIC64_ALTERNATIVE(add_unless) "\n\t"
- : "+A" (a), "+c" (v), "+S" (low), "+D" (high)
- : : "memory");
+ alternative_atomic64(add_unless,
+ ASM_OUTPUT2("+A" (a), "+c" (low), "+D" (high)),
+ "S" (v) : "memory");
return (int)a;
}
@@ -279,26 +297,20 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
static inline int atomic64_inc_not_zero(atomic64_t *v)
{
int r;
- asm volatile(ATOMIC64_ALTERNATIVE(inc_not_zero)
- : "=a" (r)
- : "S" (v)
- : "ecx", "edx", "memory"
- );
+ alternative_atomic64(inc_not_zero, "=&a" (r),
+ "S" (v) : "ecx", "edx", "memory");
return r;
}
static inline long long atomic64_dec_if_positive(atomic64_t *v)
{
long long r;
- asm volatile(ATOMIC64_ALTERNATIVE(dec_if_positive)
- : "=A" (r)
- : "S" (v)
- : "ecx", "memory"
- );
+ alternative_atomic64(dec_if_positive, "=&A" (r),
+ "S" (v) : "ecx", "memory");
return r;
}
-#undef ATOMIC64_ALTERNATIVE
-#undef ATOMIC64_ALTERNATIVE_
+#undef alternative_atomic64
+#undef __alternative_atomic64
#endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/auxvec.h b/arch/x86/include/asm/auxvec.h
index 1316b4c3542..77203ac352d 100644
--- a/arch/x86/include/asm/auxvec.h
+++ b/arch/x86/include/asm/auxvec.h
@@ -9,4 +9,11 @@
#endif
#define AT_SYSINFO_EHDR 33
+/* entries in ARCH_DLINFO: */
+#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
+# define AT_VECTOR_SIZE_ARCH 2
+#else /* else it's non-compat x86-64 */
+# define AT_VECTOR_SIZE_ARCH 1
+#endif
+
#endif /* _ASM_X86_AUXVEC_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
new file mode 100644
index 00000000000..c6cd358a1ee
--- /dev/null
+++ b/arch/x86/include/asm/barrier.h
@@ -0,0 +1,116 @@
+#ifndef _ASM_X86_BARRIER_H
+#define _ASM_X86_BARRIER_H
+
+#include <asm/alternative.h>
+#include <asm/nops.h>
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#ifdef CONFIG_X86_32
+/*
+ * Some non-Intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#else
+#define mb() asm volatile("mfence":::"memory")
+#define rmb() asm volatile("lfence":::"memory")
+#define wmb() asm volatile("sfence" ::: "memory")
+#endif
+
+/**
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier. All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads. This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies. See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ * CPU 0 CPU 1
+ *
+ * b = 2;
+ * memory_barrier();
+ * p = &b; q = p;
+ * read_barrier_depends();
+ * d = *q;
+ * </programlisting>
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends(). However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ * CPU 0 CPU 1
+ *
+ * a = 2;
+ * memory_barrier();
+ * b = 3; y = b;
+ * read_barrier_depends();
+ * x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b". Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb()
+ * in cases like this where there are no data dependencies.
+ **/
+
+#define read_barrier_depends() do { } while (0)
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#ifdef CONFIG_X86_PPRO_FENCE
+# define smp_rmb() rmb()
+#else
+# define smp_rmb() barrier()
+#endif
+#ifdef CONFIG_X86_OOSTORE
+# define smp_wmb() wmb()
+#else
+# define smp_wmb() barrier()
+#endif
+#define smp_read_barrier_depends() read_barrier_depends()
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#else
+#define smp_mb() barrier()
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#define smp_read_barrier_depends() do { } while (0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif
+
+/*
+ * Stop RDTSC speculation. This is needed when you need to use RDTSC
+ * (or get_cycles or vread that possibly accesses the TSC) in a defined
+ * code region.
+ *
+ * (Could use an alternative three way for this if there was one.)
+ */
+static __always_inline void rdtsc_barrier(void)
+{
+ alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
+ alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+}
+
+#endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index f654d1bb17f..11e1152222d 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -36,4 +36,8 @@ do { \
#endif /* !CONFIG_BUG */
#include <asm-generic/bug.h>
+
+
+extern void show_regs_common(void);
+
#endif /* _ASM_X86_BUG_H */
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 4e12668711e..9863ee3747d 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -3,6 +3,7 @@
/* Caches aren't brain-dead on the intel. */
#include <asm-generic/cacheflush.h>
+#include <asm/special_insns.h>
#ifdef CONFIG_X86_PAT
/*
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 30d737ef2a4..d6805798d6f 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -6,7 +6,9 @@
*/
#include <linux/types.h>
#include <linux/sched.h>
+#include <asm/processor.h>
#include <asm/user32.h>
+#include <asm/unistd.h>
#define COMPAT_USER_HZ 100
#define COMPAT_UTS_MACHINE "i686\0\0"
@@ -186,7 +188,20 @@ struct compat_shmid64_ds {
/*
* The type of struct elf_prstatus.pr_reg in compatible core dumps.
*/
+#ifdef CONFIG_X86_X32_ABI
+typedef struct user_regs_struct compat_elf_gregset_t;
+
+#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216)
+#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296)
+#define SET_PR_FPVALID(S,V) \
+ do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \
+ while (0)
+
+#define COMPAT_USE_64BIT_TIME \
+ (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT))
+#else
typedef struct user_regs_struct32 compat_elf_gregset_t;
+#endif
/*
* A pointer passed in from user mode. This should not
@@ -208,13 +223,30 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
static inline void __user *arch_compat_alloc_user_space(long len)
{
- struct pt_regs *regs = task_pt_regs(current);
- return (void __user *)regs->sp - len;
+ compat_uptr_t sp;
+
+ if (test_thread_flag(TIF_IA32)) {
+ sp = task_pt_regs(current)->sp;
+ } else {
+ /* -128 for the x32 ABI redzone */
+ sp = percpu_read(old_rsp) - 128;
+ }
+
+ return (void __user *)round_down(sp - len, 16);
+}
+
+static inline bool is_x32_task(void)
+{
+#ifdef CONFIG_X86_X32_ABI
+ if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)
+ return true;
+#endif
+ return false;
}
-static inline int is_compat_task(void)
+static inline bool is_compat_task(void)
{
- return current_thread_info()->status & TS_COMPAT;
+ return is_ia32_task() || is_x32_task();
}
#endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
new file mode 100644
index 00000000000..ff501e511d9
--- /dev/null
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -0,0 +1,13 @@
+#ifndef _CPU_DEVICE_ID
+#define _CPU_DEVICE_ID 1
+
+/*
+ * Declare drivers belonging to specific x86 CPUs
+ * Similar in spirit to pci_device_id and related PCI functions
+ */
+
+#include <linux/mod_devicetable.h>
+
+extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
+
+#endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 8d67d428b0f..340ee49961a 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -177,6 +177,7 @@
#define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */
#define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */
#define X86_FEATURE_DTS (7*32+ 7) /* Digital Thermal Sensor */
+#define X86_FEATURE_HW_PSTATE (7*32+ 8) /* AMD HW-PState */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */
@@ -199,10 +200,13 @@
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
#define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
#define X86_FEATURE_BMI1 (9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE (9*32+ 4) /* Hardware Lock Elision */
#define X86_FEATURE_AVX2 (9*32+ 5) /* AVX2 instructions */
#define X86_FEATURE_SMEP (9*32+ 7) /* Supervisor Mode Execution Protection */
#define X86_FEATURE_BMI2 (9*32+ 8) /* 2nd group bit manipulation extensions */
#define X86_FEATURE_ERMS (9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID (9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */
#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index b903d5ea394..2d91580bf22 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -78,8 +78,75 @@
*/
#ifdef __KERNEL__
+#include <linux/bug.h>
+
DECLARE_PER_CPU(unsigned long, cpu_dr7);
+#ifndef CONFIG_PARAVIRT
+/*
+ * These special macros can be used to get or set a debugging register
+ */
+#define get_debugreg(var, register) \
+ (var) = native_get_debugreg(register)
+#define set_debugreg(value, register) \
+ native_set_debugreg(register, value)
+#endif
+
+static inline unsigned long native_get_debugreg(int regno)
+{
+ unsigned long val = 0; /* Damn you, gcc! */
+
+ switch (regno) {
+ case 0:
+ asm("mov %%db0, %0" :"=r" (val));
+ break;
+ case 1:
+ asm("mov %%db1, %0" :"=r" (val));
+ break;
+ case 2:
+ asm("mov %%db2, %0" :"=r" (val));
+ break;
+ case 3:
+ asm("mov %%db3, %0" :"=r" (val));
+ break;
+ case 6:
+ asm("mov %%db6, %0" :"=r" (val));
+ break;
+ case 7:
+ asm("mov %%db7, %0" :"=r" (val));
+ break;
+ default:
+ BUG();
+ }
+ return val;
+}
+
+static inline void native_set_debugreg(int regno, unsigned long value)
+{
+ switch (regno) {
+ case 0:
+ asm("mov %0, %%db0" ::"r" (value));
+ break;
+ case 1:
+ asm("mov %0, %%db1" ::"r" (value));
+ break;
+ case 2:
+ asm("mov %0, %%db2" ::"r" (value));
+ break;
+ case 3:
+ asm("mov %0, %%db3" ::"r" (value));
+ break;
+ case 6:
+ asm("mov %0, %%db6" ::"r" (value));
+ break;
+ case 7:
+ asm("mov %0, %%db7" ::"r" (value));
+ break;
+ default:
+ BUG();
+ }
+}
+
static inline void hw_breakpoint_disable(void)
{
/* Zero the control register for HW Breakpoint */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 00b222fa06b..e95822d683f 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -5,7 +5,6 @@
#include <asm/ldt.h>
#include <asm/mmu.h>
-#include <linux/mm_types.h>
#include <linux/smp.h>
static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info)
@@ -100,9 +99,6 @@ static inline int desc_empty(const void *ptr)
#define load_TLS(t, cpu) native_load_tls(t, cpu)
#define set_ldt native_set_ldt
-#ifdef CONFIG_X86_32
-#define load_user_cs_desc native_load_user_cs_desc
-#endif /*CONFIG_X86_32*/
#define write_ldt_entry(dt, entry, desc) native_write_ldt_entry(dt, entry, desc)
#define write_gdt_entry(dt, entry, desc, type) native_write_gdt_entry(dt, entry, desc, type)
@@ -408,25 +404,4 @@ static inline void set_system_intr_gate_ist(int n, void *addr, unsigned ist)
_set_gate(n, GATE_INTERRUPT, addr, 0x3, ist, __KERNEL_CS);
}
-#ifdef CONFIG_X86_32
-static inline void set_user_cs(struct desc_struct *desc, unsigned long limit)
-{
- limit = (limit - 1) / PAGE_SIZE;
- desc->a = limit & 0xffff;
- desc->b = (limit & 0xf0000) | 0x00c0fb00;
-}
-
-static inline void native_load_user_cs_desc(int cpu, struct mm_struct *mm)
-{
- get_cpu_gdt_table(cpu)[GDT_ENTRY_DEFAULT_USER_CS] = (mm)->context.user_cs;
-}
-
-#define arch_add_exec_range arch_add_exec_range
-#define arch_remove_exec_range arch_remove_exec_range
-#define arch_flush_exec_range arch_flush_exec_range
-extern void arch_add_exec_range(struct mm_struct *mm, unsigned long limit);
-extern void arch_remove_exec_range(struct mm_struct *mm, unsigned long limit);
-extern void arch_flush_exec_range(struct mm_struct *mm);
-#endif /* CONFIG_X86_32 */
-
#endif /* _ASM_X86_DESC_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index ed3065fd631..4b4331d7193 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -59,7 +59,8 @@ extern int dma_supported(struct device *hwdev, u64 mask);
extern int dma_set_mask(struct device *dev, u64 mask);
extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_addr, gfp_t flag);
+ dma_addr_t *dma_addr, gfp_t flag,
+ struct dma_attrs *attrs);
static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
{
@@ -111,9 +112,11 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
return gfp;
}
+#define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL)
+
static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp)
+dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, struct dma_attrs *attrs)
{
struct dma_map_ops *ops = get_dma_ops(dev);
void *memory;
@@ -129,18 +132,21 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
if (!is_device_dma_capable(dev))
return NULL;
- if (!ops->alloc_coherent)
+ if (!ops->alloc)
return NULL;
- memory = ops->alloc_coherent(dev, size, dma_handle,
- dma_alloc_coherent_gfp_flags(dev, gfp));
+ memory = ops->alloc(dev, size, dma_handle,
+ dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
return memory;
}
-static inline void dma_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t bus)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t bus,
+ struct dma_attrs *attrs)
{
struct dma_map_ops *ops = get_dma_ops(dev);
@@ -150,8 +156,8 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
return;
debug_dma_free_coherent(dev, size, vaddr, bus);
- if (ops->free_coherent)
- ops->free_coherent(dev, size, vaddr, bus);
+ if (ops->free)
+ ops->free(dev, size, vaddr, bus, attrs);
}
#endif
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 844f735fd63..c9dcc181d4d 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -95,7 +95,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
extern int add_efi_memmap;
extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
-extern void efi_memblock_x86_reserve_range(void);
+extern int efi_memblock_x86_reserve_range(void);
extern void efi_call_phys_prelog(void);
extern void efi_call_phys_epilog(void);
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 5f962df30d0..5939f44fe0c 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -84,7 +84,6 @@ extern unsigned int vdso_enabled;
(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
#include <asm/processor.h>
-#include <asm/system.h>
#ifdef CONFIG_X86_32
#include <asm/desc.h>
@@ -156,7 +155,12 @@ do { \
#define elf_check_arch(x) \
((x)->e_machine == EM_X86_64)
-#define compat_elf_check_arch(x) elf_check_arch_ia32(x)
+#define compat_elf_check_arch(x) \
+ (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+
+#if __USER32_DS != __USER_DS
+# error "The following code assumes __USER32_DS == __USER_DS"
+#endif
static inline void elf_common_init(struct thread_struct *t,
struct pt_regs *regs, const u16 ds)
@@ -179,8 +183,9 @@ static inline void elf_common_init(struct thread_struct *t,
void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp);
#define compat_start_thread start_thread_ia32
-void set_personality_ia32(void);
-#define COMPAT_SET_PERSONALITY(ex) set_personality_ia32()
+void set_personality_ia32(bool);
+#define COMPAT_SET_PERSONALITY(ex) \
+ set_personality_ia32((ex).e_machine == EM_X86_64)
#define COMPAT_ELF_PLATFORM ("i686")
@@ -287,7 +292,7 @@ do { \
#define VDSO_HIGH_BASE 0xffffe000U /* CONFIG_COMPAT_VDSO address */
/* 1GB for 64bit, 8MB for 32bit */
-#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
+#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff)
#define ARCH_DLINFO \
do { \
@@ -296,9 +301,20 @@ do { \
(unsigned long)current->mm->context.vdso); \
} while (0)
+#define ARCH_DLINFO_X32 \
+do { \
+ if (vdso_enabled) \
+ NEW_AUX_ENT(AT_SYSINFO_EHDR, \
+ (unsigned long)current->mm->context.vdso); \
+} while (0)
+
#define AT_SYSINFO 32
-#define COMPAT_ARCH_DLINFO ARCH_DLINFO_IA32(sysctl_vsyscall32)
+#define COMPAT_ARCH_DLINFO \
+if (test_thread_flag(TIF_X32)) \
+ ARCH_DLINFO_X32; \
+else \
+ ARCH_DLINFO_IA32(sysctl_vsyscall32)
#define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000)
@@ -314,6 +330,8 @@ struct linux_binprm;
#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
int uses_interp);
+extern int x32_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp);
extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
#define compat_arch_setup_additional_pages syscall32_setup_pages
@@ -330,7 +348,7 @@ static inline int mmap_is_ia32(void)
return 1;
#endif
#ifdef CONFIG_IA32_EMULATION
- if (test_thread_flag(TIF_IA32))
+ if (test_thread_flag(TIF_ADDR32))
return 1;
#endif
return 0;
diff --git a/arch/x86/include/asm/exec.h b/arch/x86/include/asm/exec.h
new file mode 100644
index 00000000000..54c2e1db274
--- /dev/null
+++ b/arch/x86/include/asm/exec.h
@@ -0,0 +1 @@
+/* define arch_align_stack() here */
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
new file mode 100644
index 00000000000..4fa88154e4d
--- /dev/null
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -0,0 +1,520 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _FPU_INTERNAL_H
+#define _FPU_INTERNAL_H
+
+#include <linux/kernel_stat.h>
+#include <linux/regset.h>
+#include <linux/slab.h>
+#include <asm/asm.h>
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+#include <asm/uaccess.h>
+#include <asm/xsave.h>
+
+extern unsigned int sig_xstate_size;
+extern void fpu_init(void);
+
+DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
+
+extern user_regset_active_fn fpregs_active, xfpregs_active;
+extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
+ xstateregs_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
+ xstateregs_set;
+
+
+/*
+ * xstateregs_active == fpregs_active. Please refer to the comment
+ * at the definition of fpregs_active.
+ */
+#define xstateregs_active fpregs_active
+
+extern struct _fpx_sw_bytes fx_sw_reserved;
+#ifdef CONFIG_IA32_EMULATION
+extern unsigned int sig_xstate_ia32_size;
+extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
+struct _fpstate_ia32;
+struct _xstate_ia32;
+extern int save_i387_xstate_ia32(void __user *buf);
+extern int restore_i387_xstate_ia32(void __user *buf);
+#endif
+
+#ifdef CONFIG_MATH_EMULATION
+extern void finit_soft_fpu(struct i387_soft_struct *soft);
+#else
+static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
+#endif
+
+#define X87_FSW_ES (1 << 7) /* Exception Summary */
+
+static __always_inline __pure bool use_xsaveopt(void)
+{
+ return static_cpu_has(X86_FEATURE_XSAVEOPT);
+}
+
+static __always_inline __pure bool use_xsave(void)
+{
+ return static_cpu_has(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+ return static_cpu_has(X86_FEATURE_FXSR);
+}
+
+extern void __sanitize_i387_state(struct task_struct *);
+
+static inline void sanitize_i387_state(struct task_struct *tsk)
+{
+ if (!use_xsaveopt())
+ return;
+ __sanitize_i387_state(tsk);
+}
+
+#ifdef CONFIG_X86_64
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
+{
+ int err;
+
+ /* See comment in fxsave() below. */
+#ifdef CONFIG_AS_FXSAVEQ
+ asm volatile("1: fxrstorq %[fx]\n\t"
+ "2:\n"
+ ".section .fixup,\"ax\"\n"
+ "3: movl $-1,%[err]\n"
+ " jmp 2b\n"
+ ".previous\n"
+ _ASM_EXTABLE(1b, 3b)
+ : [err] "=r" (err)
+ : [fx] "m" (*fx), "0" (0));
+#else
+ asm volatile("1: rex64/fxrstor (%[fx])\n\t"
+ "2:\n"
+ ".section .fixup,\"ax\"\n"
+ "3: movl $-1,%[err]\n"
+ " jmp 2b\n"
+ ".previous\n"
+ _ASM_EXTABLE(1b, 3b)
+ : [err] "=r" (err)
+ : [fx] "R" (fx), "m" (*fx), "0" (0));
+#endif
+ return err;
+}
+
+static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
+{
+ int err;
+
+ /*
+ * Clear the bytes not touched by the fxsave and reserved
+ * for the SW usage.
+ */
+ err = __clear_user(&fx->sw_reserved,
+ sizeof(struct _fpx_sw_bytes));
+ if (unlikely(err))
+ return -EFAULT;
+
+ /* See comment in fxsave() below. */
+#ifdef CONFIG_AS_FXSAVEQ
+ asm volatile("1: fxsaveq %[fx]\n\t"
+ "2:\n"
+ ".section .fixup,\"ax\"\n"
+ "3: movl $-1,%[err]\n"
+ " jmp 2b\n"
+ ".previous\n"
+ _ASM_EXTABLE(1b, 3b)
+ : [err] "=r" (err), [fx] "=m" (*fx)
+ : "0" (0));
+#else
+ asm volatile("1: rex64/fxsave (%[fx])\n\t"
+ "2:\n"
+ ".section .fixup,\"ax\"\n"
+ "3: movl $-1,%[err]\n"
+ " jmp 2b\n"
+ ".previous\n"
+ _ASM_EXTABLE(1b, 3b)
+ : [err] "=r" (err), "=m" (*fx)
+ : [fx] "R" (fx), "0" (0));
+#endif
+ if (unlikely(err) &&
+ __clear_user(fx, sizeof(struct i387_fxsave_struct)))
+ err = -EFAULT;
+ /* No need to clear here because the caller clears USED_MATH */
+ return err;
+}
+
+static inline void fpu_fxsave(struct fpu *fpu)
+{
+ /* Using "rex64; fxsave %0" is broken because, if the memory operand
+ uses any extended registers for addressing, a second REX prefix
+ will be generated (to the assembler, rex64 followed by semicolon
+ is a separate instruction), and hence the 64-bitness is lost. */
+
+#ifdef CONFIG_AS_FXSAVEQ
+ /* Using "fxsaveq %0" would be the ideal choice, but is only supported
+ starting with gas 2.16. */
+ __asm__ __volatile__("fxsaveq %0"
+ : "=m" (fpu->state->fxsave));
+#else
+ /* Using, as a workaround, the properly prefixed form below isn't
+ accepted by any binutils version so far released, complaining that
+ the same type of prefix is used twice if an extended register is
+ needed for addressing (fix submitted to mainline 2005-11-21).
+ asm volatile("rex64/fxsave %0"
+ : "=m" (fpu->state->fxsave));
+ This, however, we can work around by forcing the compiler to select
+ an addressing mode that doesn't require extended registers. */
+ asm volatile("rex64/fxsave (%[fx])"
+ : "=m" (fpu->state->fxsave)
+ : [fx] "R" (&fpu->state->fxsave));
+#endif
+}
+
+#else /* CONFIG_X86_32 */
+
+/* perform fxrstor iff the processor has extended states, otherwise frstor */
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
+{
+ /*
+ * The "nop" is needed to make the instructions the same
+ * length.
+ */
+ alternative_input(
+ "nop ; frstor %1",
+ "fxrstor %1",
+ X86_FEATURE_FXSR,
+ "m" (*fx));
+
+ return 0;
+}
+
+static inline void fpu_fxsave(struct fpu *fpu)
+{
+ asm volatile("fxsave %[fx]"
+ : [fx] "=m" (fpu->state->fxsave));
+}
+
+#endif /* CONFIG_X86_64 */
+
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact.
+ */
+static inline int fpu_save_init(struct fpu *fpu)
+{
+ if (use_xsave()) {
+ fpu_xsave(fpu);
+
+ /*
+ * xsave header may indicate the init state of the FP.
+ */
+ if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
+ return 1;
+ } else if (use_fxsr()) {
+ fpu_fxsave(fpu);
+ } else {
+ asm volatile("fnsave %[fx]; fwait"
+ : [fx] "=m" (fpu->state->fsave));
+ return 0;
+ }
+
+ /*
+ * If exceptions are pending, we need to clear them so
+ * that we don't randomly get exceptions later.
+ *
+ * FIXME! Is this perhaps only true for the old-style
+ * irq13 case? Maybe we could leave the x87 state
+ * intact otherwise?
+ */
+ if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
+ asm volatile("fnclex");
+ return 0;
+ }
+ return 1;
+}
+
+static inline int __save_init_fpu(struct task_struct *tsk)
+{
+ return fpu_save_init(&tsk->thread.fpu);
+}
+
+static inline int fpu_fxrstor_checking(struct fpu *fpu)
+{
+ return fxrstor_checking(&fpu->state->fxsave);
+}
+
+static inline int fpu_restore_checking(struct fpu *fpu)
+{
+ if (use_xsave())
+ return fpu_xrstor_checking(fpu);
+ else
+ return fpu_fxrstor_checking(fpu);
+}
+
+static inline int restore_fpu_checking(struct task_struct *tsk)
+{
+ /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+ is pending. Clear the x87 state here by setting it to fixed
+ values. "m" is a random variable that should be in L1 */
+ alternative_input(
+ ASM_NOP8 ASM_NOP2,
+ "emms\n\t" /* clear stack tags */
+ "fildl %P[addr]", /* set F?P to defined value */
+ X86_FEATURE_FXSAVE_LEAK,
+ [addr] "m" (tsk->thread.fpu.has_fpu));
+
+ return fpu_restore_checking(&tsk->thread.fpu);
+}
+
+/*
+ * Software FPU state helpers. Careful: these need to
+ * be preemption protection *and* they need to be
+ * properly paired with the CR0.TS changes!
+ */
+static inline int __thread_has_fpu(struct task_struct *tsk)
+{
+ return tsk->thread.fpu.has_fpu;
+}
+
+/* Must be paired with an 'stts' after! */
+static inline void __thread_clear_has_fpu(struct task_struct *tsk)
+{
+ tsk->thread.fpu.has_fpu = 0;
+ percpu_write(fpu_owner_task, NULL);
+}
+
+/* Must be paired with a 'clts' before! */
+static inline void __thread_set_has_fpu(struct task_struct *tsk)
+{
+ tsk->thread.fpu.has_fpu = 1;
+ percpu_write(fpu_owner_task, tsk);
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void __thread_fpu_end(struct task_struct *tsk)
+{
+ __thread_clear_has_fpu(tsk);
+ stts();
+}
+
+static inline void __thread_fpu_begin(struct task_struct *tsk)
+{
+ clts();
+ __thread_set_has_fpu(tsk);
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ * - switch_fpu_prepare() saves the old state and
+ * sets the new state of the CR0.TS bit. This is
+ * done within the context of the old process.
+ *
+ * - switch_fpu_finish() restores the new state as
+ * necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+/*
+ * FIXME! We could do a totally lazy restore, but we need to
+ * add a per-cpu "this was the task that last touched the FPU
+ * on this CPU" variable, and the task needs to have a "I last
+ * touched the FPU on this CPU" and check them.
+ *
+ * We don't do that yet, so "fpu_lazy_restore()" always returns
+ * false, but some day..
+ */
+static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
+{
+ return new == percpu_read_stable(fpu_owner_task) &&
+ cpu == new->thread.fpu.last_cpu;
+}
+
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
+{
+ fpu_switch_t fpu;
+
+ fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+ if (__thread_has_fpu(old)) {
+ if (!__save_init_fpu(old))
+ cpu = ~0;
+ old->thread.fpu.last_cpu = cpu;
+ old->thread.fpu.has_fpu = 0; /* But leave fpu_owner_task! */
+
+ /* Don't change CR0.TS if we just switch! */
+ if (fpu.preload) {
+ new->fpu_counter++;
+ __thread_set_has_fpu(new);
+ prefetch(new->thread.fpu.state);
+ } else
+ stts();
+ } else {
+ old->fpu_counter = 0;
+ old->thread.fpu.last_cpu = ~0;
+ if (fpu.preload) {
+ new->fpu_counter++;
+ if (fpu_lazy_restore(new, cpu))
+ fpu.preload = 0;
+ else
+ prefetch(new->thread.fpu.state);
+ __thread_fpu_begin(new);
+ }
+ }
+ return fpu;
+}
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
+{
+ if (fpu.preload) {
+ if (unlikely(restore_fpu_checking(new)))
+ __thread_fpu_end(new);
+ }
+}
+
+/*
+ * Signal frame handlers...
+ */
+extern int save_i387_xstate(void __user *buf);
+extern int restore_i387_xstate(void __user *buf);
+
+static inline void __clear_fpu(struct task_struct *tsk)
+{
+ if (__thread_has_fpu(tsk)) {
+ /* Ignore delayed exceptions from user space */
+ asm volatile("1: fwait\n"
+ "2:\n"
+ _ASM_EXTABLE(1b, 2b));
+ __thread_fpu_end(tsk);
+ }
+}
+
+/*
+ * The actual user_fpu_begin/end() functions
+ * need to be preemption-safe.
+ *
+ * NOTE! user_fpu_end() must be used only after you
+ * have saved the FP state, and user_fpu_begin() must
+ * be used only immediately before restoring it.
+ * These functions do not do any save/restore on
+ * their own.
+ */
+static inline void user_fpu_end(void)
+{
+ preempt_disable();
+ __thread_fpu_end(current);
+ preempt_enable();
+}
+
+static inline void user_fpu_begin(void)
+{
+ preempt_disable();
+ if (!user_has_fpu())
+ __thread_fpu_begin(current);
+ preempt_enable();
+}
+
+/*
+ * These disable preemption on their own and are safe
+ */
+static inline void save_init_fpu(struct task_struct *tsk)
+{
+ WARN_ON_ONCE(!__thread_has_fpu(tsk));
+ preempt_disable();
+ __save_init_fpu(tsk);
+ __thread_fpu_end(tsk);
+ preempt_enable();
+}
+
+static inline void clear_fpu(struct task_struct *tsk)
+{
+ preempt_disable();
+ __clear_fpu(tsk);
+ preempt_enable();
+}
+
+/*
+ * i387 state interaction
+ */
+static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
+{
+ if (cpu_has_fxsr) {
+ return tsk->thread.fpu.state->fxsave.cwd;
+ } else {
+ return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
+ }
+}
+
+static inline unsigned short get_fpu_swd(struct task_struct *tsk)
+{
+ if (cpu_has_fxsr) {
+ return tsk->thread.fpu.state->fxsave.swd;
+ } else {
+ return (unsigned short)tsk->thread.fpu.state->fsave.swd;
+ }
+}
+
+static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
+{
+ if (cpu_has_xmm) {
+ return tsk->thread.fpu.state->fxsave.mxcsr;
+ } else {
+ return MXCSR_DEFAULT;
+ }
+}
+
+static bool fpu_allocated(struct fpu *fpu)
+{
+ return fpu->state != NULL;
+}
+
+static inline int fpu_alloc(struct fpu *fpu)
+{
+ if (fpu_allocated(fpu))
+ return 0;
+ fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
+ if (!fpu->state)
+ return -ENOMEM;
+ WARN_ON((unsigned long)fpu->state & 15);
+ return 0;
+}
+
+static inline void fpu_free(struct fpu *fpu)
+{
+ if (fpu->state) {
+ kmem_cache_free(task_xstate_cachep, fpu->state);
+ fpu->state = NULL;
+ }
+}
+
+static inline void fpu_copy(struct fpu *dst, struct fpu *src)
+{
+ memcpy(dst->state, src->state, xstate_size);
+}
+
+extern void fpu_finit(struct fpu *fpu);
+
+#endif
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index d09bb03653f..71ecbcba1a4 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -9,7 +9,6 @@
#include <asm/asm.h>
#include <asm/errno.h>
#include <asm/processor.h>
-#include <asm/system.h>
#define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \
asm volatile("1:\t" insn "\n" \
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index da0b3ca815b..382f75d735f 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -7,7 +7,6 @@
typedef struct {
unsigned int __softirq_pending;
unsigned int __nmi_count; /* arch dependent */
- unsigned int irq0_irqs;
#ifdef CONFIG_X86_LOCAL_APIC
unsigned int apic_timer_irqs; /* arch dependent */
unsigned int irq_spurious_count;
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 3bd04022fd0..302a323b3f6 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -61,7 +61,7 @@ void *kmap(struct page *page);
void kunmap(struct page *page);
void *kmap_atomic_prot(struct page *page, pgprot_t prot);
-void *__kmap_atomic(struct page *page);
+void *kmap_atomic(struct page *page);
void __kunmap_atomic(void *kvaddr);
void *kmap_atomic_pfn(unsigned long pfn);
void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 247904945d3..257d9cca214 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -13,476 +13,18 @@
#ifndef __ASSEMBLY__
#include <linux/sched.h>
-#include <linux/kernel_stat.h>
-#include <linux/regset.h>
#include <linux/hardirq.h>
-#include <linux/slab.h>
-#include <asm/asm.h>
-#include <asm/cpufeature.h>
-#include <asm/processor.h>
-#include <asm/sigcontext.h>
-#include <asm/user.h>
-#include <asm/uaccess.h>
-#include <asm/xsave.h>
-extern unsigned int sig_xstate_size;
-extern void fpu_init(void);
-extern void mxcsr_feature_mask_init(void);
+struct pt_regs;
+struct user_i387_struct;
+
extern int init_fpu(struct task_struct *child);
-extern void math_state_restore(void);
extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
+extern void math_state_restore(void);
-DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
-
-extern user_regset_active_fn fpregs_active, xfpregs_active;
-extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
- xstateregs_get;
-extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
- xstateregs_set;
-
-/*
- * xstateregs_active == fpregs_active. Please refer to the comment
- * at the definition of fpregs_active.
- */
-#define xstateregs_active fpregs_active
-
-extern struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-extern unsigned int sig_xstate_ia32_size;
-extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
-struct _fpstate_ia32;
-struct _xstate_ia32;
-extern int save_i387_xstate_ia32(void __user *buf);
-extern int restore_i387_xstate_ia32(void __user *buf);
-#endif
-
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-#define X87_FSW_ES (1 << 7) /* Exception Summary */
-
-static __always_inline __pure bool use_xsaveopt(void)
-{
- return static_cpu_has(X86_FEATURE_XSAVEOPT);
-}
-
-static __always_inline __pure bool use_xsave(void)
-{
- return static_cpu_has(X86_FEATURE_XSAVE);
-}
-
-static __always_inline __pure bool use_fxsr(void)
-{
- return static_cpu_has(X86_FEATURE_FXSR);
-}
-
-extern void __sanitize_i387_state(struct task_struct *);
-
-static inline void sanitize_i387_state(struct task_struct *tsk)
-{
- if (!use_xsaveopt())
- return;
- __sanitize_i387_state(tsk);
-}
-
-#ifdef CONFIG_X86_64
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
- int err;
-
- /* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
- asm volatile("1: fxrstorq %[fx]\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err)
- : [fx] "m" (*fx), "0" (0));
-#else
- asm volatile("1: rex64/fxrstor (%[fx])\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err)
- : [fx] "R" (fx), "m" (*fx), "0" (0));
-#endif
- return err;
-}
-
-static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
-{
- int err;
-
- /*
- * Clear the bytes not touched by the fxsave and reserved
- * for the SW usage.
- */
- err = __clear_user(&fx->sw_reserved,
- sizeof(struct _fpx_sw_bytes));
- if (unlikely(err))
- return -EFAULT;
-
- /* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
- asm volatile("1: fxsaveq %[fx]\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err), [fx] "=m" (*fx)
- : "0" (0));
-#else
- asm volatile("1: rex64/fxsave (%[fx])\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err), "=m" (*fx)
- : [fx] "R" (fx), "0" (0));
-#endif
- if (unlikely(err) &&
- __clear_user(fx, sizeof(struct i387_fxsave_struct)))
- err = -EFAULT;
- /* No need to clear here because the caller clears USED_MATH */
- return err;
-}
-
-static inline void fpu_fxsave(struct fpu *fpu)
-{
- /* Using "rex64; fxsave %0" is broken because, if the memory operand
- uses any extended registers for addressing, a second REX prefix
- will be generated (to the assembler, rex64 followed by semicolon
- is a separate instruction), and hence the 64-bitness is lost. */
-
-#ifdef CONFIG_AS_FXSAVEQ
- /* Using "fxsaveq %0" would be the ideal choice, but is only supported
- starting with gas 2.16. */
- __asm__ __volatile__("fxsaveq %0"
- : "=m" (fpu->state->fxsave));
-#else
- /* Using, as a workaround, the properly prefixed form below isn't
- accepted by any binutils version so far released, complaining that
- the same type of prefix is used twice if an extended register is
- needed for addressing (fix submitted to mainline 2005-11-21).
- asm volatile("rex64/fxsave %0"
- : "=m" (fpu->state->fxsave));
- This, however, we can work around by forcing the compiler to select
- an addressing mode that doesn't require extended registers. */
- asm volatile("rex64/fxsave (%[fx])"
- : "=m" (fpu->state->fxsave)
- : [fx] "R" (&fpu->state->fxsave));
-#endif
-}
-
-#else /* CONFIG_X86_32 */
-
-/* perform fxrstor iff the processor has extended states, otherwise frstor */
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
- /*
- * The "nop" is needed to make the instructions the same
- * length.
- */
- alternative_input(
- "nop ; frstor %1",
- "fxrstor %1",
- X86_FEATURE_FXSR,
- "m" (*fx));
-
- return 0;
-}
-
-static inline void fpu_fxsave(struct fpu *fpu)
-{
- asm volatile("fxsave %[fx]"
- : [fx] "=m" (fpu->state->fxsave));
-}
-
-#endif /* CONFIG_X86_64 */
-
-/*
- * These must be called with preempt disabled. Returns
- * 'true' if the FPU state is still intact.
- */
-static inline int fpu_save_init(struct fpu *fpu)
-{
- if (use_xsave()) {
- fpu_xsave(fpu);
-
- /*
- * xsave header may indicate the init state of the FP.
- */
- if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
- return 1;
- } else if (use_fxsr()) {
- fpu_fxsave(fpu);
- } else {
- asm volatile("fnsave %[fx]; fwait"
- : [fx] "=m" (fpu->state->fsave));
- return 0;
- }
-
- /*
- * If exceptions are pending, we need to clear them so
- * that we don't randomly get exceptions later.
- *
- * FIXME! Is this perhaps only true for the old-style
- * irq13 case? Maybe we could leave the x87 state
- * intact otherwise?
- */
- if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
- asm volatile("fnclex");
- return 0;
- }
- return 1;
-}
-
-static inline int __save_init_fpu(struct task_struct *tsk)
-{
- return fpu_save_init(&tsk->thread.fpu);
-}
-
-static inline int fpu_fxrstor_checking(struct fpu *fpu)
-{
- return fxrstor_checking(&fpu->state->fxsave);
-}
-
-static inline int fpu_restore_checking(struct fpu *fpu)
-{
- if (use_xsave())
- return fpu_xrstor_checking(fpu);
- else
- return fpu_fxrstor_checking(fpu);
-}
-
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
- /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
- is pending. Clear the x87 state here by setting it to fixed
- values. "m" is a random variable that should be in L1 */
- alternative_input(
- ASM_NOP8 ASM_NOP2,
- "emms\n\t" /* clear stack tags */
- "fildl %P[addr]", /* set F?P to defined value */
- X86_FEATURE_FXSAVE_LEAK,
- [addr] "m" (tsk->thread.fpu.has_fpu));
-
- return fpu_restore_checking(&tsk->thread.fpu);
-}
-
-/*
- * Software FPU state helpers. Careful: these need to
- * be preemption protection *and* they need to be
- * properly paired with the CR0.TS changes!
- */
-static inline int __thread_has_fpu(struct task_struct *tsk)
-{
- return tsk->thread.fpu.has_fpu;
-}
-
-/* Must be paired with an 'stts' after! */
-static inline void __thread_clear_has_fpu(struct task_struct *tsk)
-{
- tsk->thread.fpu.has_fpu = 0;
- percpu_write(fpu_owner_task, NULL);
-}
-
-/* Must be paired with a 'clts' before! */
-static inline void __thread_set_has_fpu(struct task_struct *tsk)
-{
- tsk->thread.fpu.has_fpu = 1;
- percpu_write(fpu_owner_task, tsk);
-}
-
-/*
- * Encapsulate the CR0.TS handling together with the
- * software flag.
- *
- * These generally need preemption protection to work,
- * do try to avoid using these on their own.
- */
-static inline void __thread_fpu_end(struct task_struct *tsk)
-{
- __thread_clear_has_fpu(tsk);
- stts();
-}
-
-static inline void __thread_fpu_begin(struct task_struct *tsk)
-{
- clts();
- __thread_set_has_fpu(tsk);
-}
-
-/*
- * FPU state switching for scheduling.
- *
- * This is a two-stage process:
- *
- * - switch_fpu_prepare() saves the old state and
- * sets the new state of the CR0.TS bit. This is
- * done within the context of the old process.
- *
- * - switch_fpu_finish() restores the new state as
- * necessary.
- */
-typedef struct { int preload; } fpu_switch_t;
-
-/*
- * FIXME! We could do a totally lazy restore, but we need to
- * add a per-cpu "this was the task that last touched the FPU
- * on this CPU" variable, and the task needs to have a "I last
- * touched the FPU on this CPU" and check them.
- *
- * We don't do that yet, so "fpu_lazy_restore()" always returns
- * false, but some day..
- */
-static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
-{
- return new == percpu_read_stable(fpu_owner_task) &&
- cpu == new->thread.fpu.last_cpu;
-}
-
-static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
-{
- fpu_switch_t fpu;
-
- fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
- if (__thread_has_fpu(old)) {
- if (!__save_init_fpu(old))
- cpu = ~0;
- old->thread.fpu.last_cpu = cpu;
- old->thread.fpu.has_fpu = 0; /* But leave fpu_owner_task! */
-
- /* Don't change CR0.TS if we just switch! */
- if (fpu.preload) {
- new->fpu_counter++;
- __thread_set_has_fpu(new);
- prefetch(new->thread.fpu.state);
- } else
- stts();
- } else {
- old->fpu_counter = 0;
- old->thread.fpu.last_cpu = ~0;
- if (fpu.preload) {
- new->fpu_counter++;
- if (fpu_lazy_restore(new, cpu))
- fpu.preload = 0;
- else
- prefetch(new->thread.fpu.state);
- __thread_fpu_begin(new);
- }
- }
- return fpu;
-}
-
-/*
- * By the time this gets called, we've already cleared CR0.TS and
- * given the process the FPU if we are going to preload the FPU
- * state - all we need to do is to conditionally restore the register
- * state itself.
- */
-static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
-{
- if (fpu.preload) {
- if (unlikely(restore_fpu_checking(new)))
- __thread_fpu_end(new);
- }
-}
-
-/*
- * Signal frame handlers...
- */
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
-
-static inline void __clear_fpu(struct task_struct *tsk)
-{
- if (__thread_has_fpu(tsk)) {
- /* Ignore delayed exceptions from user space */
- asm volatile("1: fwait\n"
- "2:\n"
- _ASM_EXTABLE(1b, 2b));
- __thread_fpu_end(tsk);
- }
-}
-
-/*
- * Were we in an interrupt that interrupted kernel mode?
- *
- * We can do a kernel_fpu_begin/end() pair *ONLY* if that
- * pair does nothing at all: the thread must not have fpu (so
- * that we don't try to save the FPU state), and TS must
- * be set (so that the clts/stts pair does nothing that is
- * visible in the interrupted kernel thread).
- */
-static inline bool interrupted_kernel_fpu_idle(void)
-{
- return !__thread_has_fpu(current) &&
- (read_cr0() & X86_CR0_TS);
-}
-
-/*
- * Were we in user mode (or vm86 mode) when we were
- * interrupted?
- *
- * Doing kernel_fpu_begin/end() is ok if we are running
- * in an interrupt context from user mode - we'll just
- * save the FPU state as required.
- */
-static inline bool interrupted_user_mode(void)
-{
- struct pt_regs *regs = get_irq_regs();
- return regs && user_mode_vm(regs);
-}
-
-/*
- * Can we use the FPU in kernel mode with the
- * whole "kernel_fpu_begin/end()" sequence?
- *
- * It's always ok in process context (ie "not interrupt")
- * but it is sometimes ok even from an irq.
- */
-static inline bool irq_fpu_usable(void)
-{
- return !in_interrupt() ||
- interrupted_user_mode() ||
- interrupted_kernel_fpu_idle();
-}
-
-static inline void kernel_fpu_begin(void)
-{
- struct task_struct *me = current;
-
- WARN_ON_ONCE(!irq_fpu_usable());
- preempt_disable();
- if (__thread_has_fpu(me)) {
- __save_init_fpu(me);
- __thread_clear_has_fpu(me);
- /* We do 'stts()' in kernel_fpu_end() */
- } else {
- percpu_write(fpu_owner_task, NULL);
- clts();
- }
-}
-
-static inline void kernel_fpu_end(void)
-{
- stts();
- preempt_enable();
-}
+extern bool irq_fpu_usable(void);
+extern void kernel_fpu_begin(void);
+extern void kernel_fpu_end(void);
/*
* Some instructions like VIA's padlock instructions generate a spurious
@@ -524,126 +66,13 @@ static inline void irq_ts_restore(int TS_state)
* we can just assume we have FPU access - typically
* to save the FP state - we'll just take a #NM
* fault and get the FPU access back.
- *
- * The actual user_fpu_begin/end() functions
- * need to be preemption-safe, though.
- *
- * NOTE! user_fpu_end() must be used only after you
- * have saved the FP state, and user_fpu_begin() must
- * be used only immediately before restoring it.
- * These functions do not do any save/restore on
- * their own.
*/
static inline int user_has_fpu(void)
{
- return __thread_has_fpu(current);
-}
-
-static inline void user_fpu_end(void)
-{
- preempt_disable();
- __thread_fpu_end(current);
- preempt_enable();
-}
-
-static inline void user_fpu_begin(void)
-{
- preempt_disable();
- if (!user_has_fpu())
- __thread_fpu_begin(current);
- preempt_enable();
-}
-
-/*
- * These disable preemption on their own and are safe
- */
-static inline void save_init_fpu(struct task_struct *tsk)
-{
- WARN_ON_ONCE(!__thread_has_fpu(tsk));
- preempt_disable();
- __save_init_fpu(tsk);
- __thread_fpu_end(tsk);
- preempt_enable();
-}
-
-static inline void unlazy_fpu(struct task_struct *tsk)
-{
- preempt_disable();
- if (__thread_has_fpu(tsk)) {
- __save_init_fpu(tsk);
- __thread_fpu_end(tsk);
- } else
- tsk->fpu_counter = 0;
- preempt_enable();
-}
-
-static inline void clear_fpu(struct task_struct *tsk)
-{
- preempt_disable();
- __clear_fpu(tsk);
- preempt_enable();
-}
-
-/*
- * i387 state interaction
- */
-static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
-{
- if (cpu_has_fxsr) {
- return tsk->thread.fpu.state->fxsave.cwd;
- } else {
- return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
- }
-}
-
-static inline unsigned short get_fpu_swd(struct task_struct *tsk)
-{
- if (cpu_has_fxsr) {
- return tsk->thread.fpu.state->fxsave.swd;
- } else {
- return (unsigned short)tsk->thread.fpu.state->fsave.swd;
- }
-}
-
-static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
-{
- if (cpu_has_xmm) {
- return tsk->thread.fpu.state->fxsave.mxcsr;
- } else {
- return MXCSR_DEFAULT;
- }
-}
-
-static bool fpu_allocated(struct fpu *fpu)
-{
- return fpu->state != NULL;
-}
-
-static inline int fpu_alloc(struct fpu *fpu)
-{
- if (fpu_allocated(fpu))
- return 0;
- fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
- if (!fpu->state)
- return -ENOMEM;
- WARN_ON((unsigned long)fpu->state & 15);
- return 0;
-}
-
-static inline void fpu_free(struct fpu *fpu)
-{
- if (fpu->state) {
- kmem_cache_free(task_xstate_cachep, fpu->state);
- fpu->state = NULL;
- }
-}
-
-static inline void fpu_copy(struct fpu *dst, struct fpu *src)
-{
- memcpy(dst->state, src->state, xstate_size);
+ return current->thread.fpu.has_fpu;
}
-extern void fpu_finit(struct fpu *fpu);
+extern void unlazy_fpu(struct task_struct *tsk);
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 1f7e6251728..ee52760549f 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -43,6 +43,15 @@ struct ucontext_ia32 {
compat_sigset_t uc_sigmask; /* mask last for extensibility */
};
+struct ucontext_x32 {
+ unsigned int uc_flags;
+ unsigned int uc_link;
+ stack_ia32_t uc_stack;
+ unsigned int uc__pad0; /* needed for alignment */
+ struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */
+ compat_sigset_t uc_sigmask; /* mask last for extensibility */
+};
+
/* This matches struct stat64 in glibc2.2, hence the absolutely
* insane amounts of padding around dev_t's.
*/
@@ -116,6 +125,15 @@ typedef struct compat_siginfo {
compat_clock_t _stime;
} _sigchld;
+ /* SIGCHLD (x32 version) */
+ struct {
+ unsigned int _pid; /* which child */
+ unsigned int _uid; /* sender's uid */
+ int _status; /* exit code */
+ compat_s64 _utime;
+ compat_s64 _stime;
+ } _sigchld_x32;
+
/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
struct {
unsigned int _addr; /* faulting insn/memory ref. */
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index f49253d7571..c5d1785373e 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -14,6 +14,7 @@ void exit_idle(void);
#else /* !CONFIG_X86_64 */
static inline void enter_idle(void) { }
static inline void exit_idle(void) { }
+static inline void __exit_idle(void) { }
#endif /* CONFIG_X86_64 */
void amd_e400_remove_cpu(int cpu);
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 205b063e3e3..74a2e312e8a 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -97,11 +97,12 @@
/* Attribute search APIs */
extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
+extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
- insn_byte_t last_pfx,
+ int lpfx_id,
insn_attr_t esc_attr);
extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
- insn_byte_t last_pfx,
+ int lpfx_id,
insn_attr_t esc_attr);
extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
insn_byte_t vex_m,
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 74df3f1eddf..48eb30a8606 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -96,12 +96,6 @@ struct insn {
#define X86_VEX_P(vex) ((vex) & 0x03) /* VEX3 Byte2, VEX2 Byte1 */
#define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */
-/* The last prefix is needed for two-byte and three-byte opcodes */
-static inline insn_byte_t insn_last_prefix(struct insn *insn)
-{
- return insn->prefixes.bytes[3];
-}
-
extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
extern void insn_get_prefixes(struct insn *insn);
extern void insn_get_opcode(struct insn *insn);
@@ -160,6 +154,18 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
return X86_VEX_P(insn->vex_prefix.bytes[2]);
}
+/* Get the last prefix id from last prefix or VEX prefix */
+static inline int insn_last_prefix_id(struct insn *insn)
+{
+ if (insn_is_avx(insn))
+ return insn_vex_p_bits(insn); /* VEX_p is a SIMD prefix id */
+
+ if (insn->prefixes.bytes[3])
+ return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
+
+ return 0;
+}
+
/* Offset of each field from kaddr */
static inline int insn_offset_rex_prefix(struct insn *insn)
{
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index ba1b11ac1cf..2c4943de515 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -5,7 +5,6 @@
#include <asm/mpspec.h>
#include <asm/apicdef.h>
#include <asm/irq_vectors.h>
-#include <asm/x86_init.h>
/*
* Intel IO-APIC support for SMP and UP systems.
@@ -22,6 +21,15 @@
#define IO_APIC_REDIR_LEVEL_TRIGGER (1 << 15)
#define IO_APIC_REDIR_MASKED (1 << 16)
+struct io_apic_ops {
+ void (*init) (void);
+ unsigned int (*read) (unsigned int apic, unsigned int reg);
+ void (*write) (unsigned int apic, unsigned int reg, unsigned int value);
+ void (*modify)(unsigned int apic, unsigned int reg, unsigned int value);
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *);
+
/*
* The structure of the IO-APIC:
*/
@@ -148,6 +156,7 @@ struct io_apic_irq_attr;
extern int io_apic_set_pci_routing(struct device *dev, int irq,
struct io_apic_irq_attr *irq_attr);
void setup_IO_APIC_irq_extra(u32 gsi);
+extern void ioapic_and_gsi_init(void);
extern void ioapic_insert_resources(void);
int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr);
@@ -176,35 +185,12 @@ extern void mp_save_irq(struct mpc_intsrc *m);
extern void disable_ioapic_support(void);
-
-void __init native_ioapic_init_mappings(void);
-unsigned int native_ioapic_read(unsigned int apic, unsigned int reg);
-void native_ioapic_write(unsigned int apic, unsigned int reg,
- unsigned int val);
-void native_ioapic_modify(unsigned int apic, unsigned int reg,
- unsigned int val);
-
-static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
-{
- return x86_ioapic.read(apic, reg);
-}
-
-static inline void io_apic_write(unsigned int apic, unsigned int reg,
- unsigned int value)
-{
- x86_ioapic.write(apic, reg, value);
-}
-
-static inline void io_apic_modify(unsigned int apic, unsigned int reg,
- unsigned int value)
-{
- x86_ioapic.modify(apic, reg, value);
-}
#else /* !CONFIG_X86_IO_APIC */
#define io_apic_assign_pci_irqs 0
#define setup_ioapic_ids_from_mpc x86_init_noop
static const int timer_through_8259 = 0;
+static inline void ioapic_and_gsi_init(void) { }
static inline void ioapic_insert_resources(void) { }
#define gsi_top (NR_IRQS_LEGACY)
static inline int mp_find_ioapic(u32 gsi) { return 0; }
@@ -226,10 +212,6 @@ static inline int restore_ioapic_entries(void)
static inline void mp_save_irq(struct mpc_intsrc *m) { };
static inline void disable_ioapic_support(void) { }
-#define native_ioapic_init_mappings NULL
-#define native_ioapic_read NULL
-#define native_ioapic_write NULL
-#define native_ioapic_modify NULL
#endif
#endif /* _ASM_X86_IO_APIC_H */
diff --git a/arch/x86/include/asm/irq_controller.h b/arch/x86/include/asm/irq_controller.h
deleted file mode 100644
index 423bbbddf36..00000000000
--- a/arch/x86/include/asm/irq_controller.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __IRQ_CONTROLLER__
-#define __IRQ_CONTROLLER__
-
-struct irq_domain {
- int (*xlate)(struct irq_domain *h, const u32 *intspec, u32 intsize,
- u32 *out_hwirq, u32 *out_type);
- void *priv;
- struct device_node *controller;
- struct list_head l;
-};
-
-#endif
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index a32b18ce6ea..3a16c1483b4 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -9,12 +9,12 @@
#define JUMP_LABEL_NOP_SIZE 5
-#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+#define STATIC_KEY_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
{
asm goto("1:"
- JUMP_LABEL_INITIAL_NOP
+ STATIC_KEY_INITIAL_NOP
".pushsection __jump_table, \"aw\" \n\t"
_ASM_ALIGN "\n\t"
_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h
index 77e95f54570..332f98c9111 100644
--- a/arch/x86/include/asm/kgdb.h
+++ b/arch/x86/include/asm/kgdb.h
@@ -64,11 +64,15 @@ enum regnames {
GDB_PS, /* 17 */
GDB_CS, /* 18 */
GDB_SS, /* 19 */
+ GDB_DS, /* 20 */
+ GDB_ES, /* 21 */
+ GDB_FS, /* 22 */
+ GDB_GS, /* 23 */
};
#define GDB_ORIG_AX 57
-#define DBG_MAX_REG_NUM 20
-/* 17 64 bit regs and 3 32 bit regs */
-#define NUMREGBYTES ((17 * 8) + (3 * 4))
+#define DBG_MAX_REG_NUM 24
+/* 17 64 bit regs and 5 32 bit regs */
+#define NUMREGBYTES ((17 * 8) + (5 * 4))
#endif /* ! CONFIG_X86_32 */
static inline void arch_kgdb_breakpoint(void)
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 4d8dcbdfc12..e7d1c194d27 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -321,4 +321,8 @@ struct kvm_xcrs {
__u64 padding[16];
};
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 7b9cfc4878a..c222e1a1b12 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -176,6 +176,7 @@ struct x86_emulate_ops {
void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr);
int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val);
+ void (*set_rflags)(struct x86_emulate_ctxt *ctxt, ulong val);
int (*cpl)(struct x86_emulate_ctxt *ctxt);
int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
@@ -388,7 +389,7 @@ bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt);
#define EMULATION_INTERCEPTED 2
int x86_emulate_insn(struct x86_emulate_ctxt *ctxt);
int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
- u16 tss_selector, int reason,
+ u16 tss_selector, int idt_index, int reason,
bool has_error_code, u32 error_code);
int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq);
#endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 52d6640a5ca..e216ba066e7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -29,7 +29,7 @@
#include <asm/msr-index.h>
#define KVM_MAX_VCPUS 254
-#define KVM_SOFT_MAX_VCPUS 64
+#define KVM_SOFT_MAX_VCPUS 160
#define KVM_MEMORY_SLOTS 32
/* memory slots that does not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 4
@@ -181,13 +181,6 @@ struct kvm_mmu_memory_cache {
void *objects[KVM_NR_MEM_OBJS];
};
-#define NR_PTE_CHAIN_ENTRIES 5
-
-struct kvm_pte_chain {
- u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
- struct hlist_node link;
-};
-
/*
* kvm_mmu_page_role, below, is defined as:
*
@@ -427,12 +420,16 @@ struct kvm_vcpu_arch {
u64 last_guest_tsc;
u64 last_kernel_ns;
- u64 last_tsc_nsec;
- u64 last_tsc_write;
- u32 virtual_tsc_khz;
+ u64 last_host_tsc;
+ u64 tsc_offset_adjustment;
+ u64 this_tsc_nsec;
+ u64 this_tsc_write;
+ u8 this_tsc_generation;
bool tsc_catchup;
- u32 tsc_catchup_mult;
- s8 tsc_catchup_shift;
+ bool tsc_always_catchup;
+ s8 virtual_tsc_shift;
+ u32 virtual_tsc_mult;
+ u32 virtual_tsc_khz;
atomic_t nmi_queued; /* unprocessed asynchronous NMIs */
unsigned nmi_pending; /* NMI queued after currently running handler */
@@ -478,6 +475,21 @@ struct kvm_vcpu_arch {
u32 id;
bool send_user_only;
} apf;
+
+ /* OSVW MSRs (AMD only) */
+ struct {
+ u64 length;
+ u64 status;
+ } osvw;
+};
+
+struct kvm_lpage_info {
+ unsigned long rmap_pde;
+ int write_count;
+};
+
+struct kvm_arch_memory_slot {
+ struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
};
struct kvm_arch {
@@ -511,8 +523,12 @@ struct kvm_arch {
s64 kvmclock_offset;
raw_spinlock_t tsc_write_lock;
u64 last_tsc_nsec;
- u64 last_tsc_offset;
u64 last_tsc_write;
+ u32 last_tsc_khz;
+ u64 cur_tsc_nsec;
+ u64 cur_tsc_write;
+ u64 cur_tsc_offset;
+ u8 cur_tsc_generation;
struct kvm_xen_hvm_config xen_hvm_config;
@@ -644,7 +660,7 @@ struct kvm_x86_ops {
u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
int (*get_lpage_level)(void);
bool (*rdtscp_supported)(void);
- void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment);
+ void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host);
void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -652,7 +668,7 @@ struct kvm_x86_ops {
bool (*has_wbinvd_exit)(void);
- void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz);
+ void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale);
void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc);
@@ -674,6 +690,17 @@ struct kvm_arch_async_pf {
extern struct kvm_x86_ops *kvm_x86_ops;
+static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
+ s64 adjustment)
+{
+ kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, false);
+}
+
+static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
+{
+ kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, true);
+}
+
int kvm_mmu_module_init(void);
void kvm_mmu_module_exit(void);
@@ -741,8 +768,8 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
-int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
- bool has_error_code, u32 error_code);
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
+ int reason, bool has_error_code, u32 error_code);
int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 734c3767cfa..183922e13de 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -170,6 +170,9 @@ static inline int kvm_para_available(void)
unsigned int eax, ebx, ecx, edx;
char signature[13];
+ if (boot_cpu_data.cpuid_level < 0)
+ return 0; /* So we don't blow up on old processors */
+
cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
memcpy(signature + 0, &ebx, 4);
memcpy(signature + 4, &ecx, 4);
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 9cdae5d47e8..c8bed0da434 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -3,7 +3,6 @@
#include <linux/percpu.h>
-#include <asm/system.h>
#include <linux/atomic.h>
#include <asm/asm.h>
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index 0e8e85bb7c5..d354fb781c5 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -5,7 +5,6 @@
#define _ASM_X86_MC146818RTC_H
#include <asm/io.h>
-#include <asm/system.h>
#include <asm/processor.h>
#include <linux/mc146818rtc.h>
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 6aefb14cbbc..441520e4174 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -151,7 +151,7 @@ static inline void enable_p5_mce(void) {}
void mce_setup(struct mce *m);
void mce_log(struct mce *m);
-extern struct device *mce_device[CONFIG_NR_CPUS];
+DECLARE_PER_CPU(struct device *, mce_device);
/*
* Maximum banks number.
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index aba94f004b7..5f55e696276 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -7,9 +7,6 @@
/*
* The x86 doesn't have a mmu context, but
* we put the segment information here.
- *
- * exec_limit is used to track the range PROT_EXEC
- * mappings span.
*/
typedef struct {
void *ldt;
@@ -22,11 +19,6 @@ typedef struct {
struct mutex lock;
void *vdso;
-
-#ifdef CONFIG_X86_32
- struct desc_struct user_cs;
- unsigned long exec_limit;
-#endif
} mm_context_t;
#ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
index 0a0a9546043..fc18bf3ce7c 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -26,8 +26,8 @@ extern struct sfi_rtc_table_entry sfi_mrtc_array[];
* identified via MSRs.
*/
enum mrst_cpu_type {
- MRST_CPU_CHIP_LINCROFT = 1,
- MRST_CPU_CHIP_PENWELL,
+ /* 1 was Moorestown */
+ MRST_CPU_CHIP_PENWELL = 2,
};
extern enum mrst_cpu_type __mrst_cpu_chip;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index a6962d9161a..ccb805966f6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -56,6 +56,13 @@
#define MSR_OFFCORE_RSP_0 0x000001a6
#define MSR_OFFCORE_RSP_1 0x000001a7
+#define MSR_LBR_SELECT 0x000001c8
+#define MSR_LBR_TOS 0x000001c9
+#define MSR_LBR_NHM_FROM 0x00000680
+#define MSR_LBR_NHM_TO 0x000006c0
+#define MSR_LBR_CORE_FROM 0x00000040
+#define MSR_LBR_CORE_TO 0x00000060
+
#define MSR_IA32_PEBS_ENABLE 0x000003f1
#define MSR_IA32_DS_AREA 0x00000600
#define MSR_IA32_PERF_CAPABILITIES 0x00000345
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index 4365ffdb461..7e3f17f92c6 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -29,18 +29,18 @@
#define MTRR_IOCTL_BASE 'M'
-struct mtrr_sentry {
- unsigned long base; /* Base address */
- unsigned int size; /* Size of region */
- unsigned int type; /* Type of region */
-};
-
/* Warning: this structure has a different order from i386
on x86-64. The 32bit emulation code takes care of that.
But you need to use this for 64bit, otherwise your X server
will break. */
#ifdef __i386__
+struct mtrr_sentry {
+ unsigned long base; /* Base address */
+ unsigned int size; /* Size of region */
+ unsigned int type; /* Type of region */
+};
+
struct mtrr_gentry {
unsigned int regnum; /* Register number */
unsigned long base; /* Base address */
@@ -50,12 +50,20 @@ struct mtrr_gentry {
#else /* __i386__ */
+struct mtrr_sentry {
+ __u64 base; /* Base address */
+ __u32 size; /* Size of region */
+ __u32 type; /* Type of region */
+};
+
struct mtrr_gentry {
- unsigned long base; /* Base address */
- unsigned int size; /* Size of region */
- unsigned int regnum; /* Register number */
- unsigned int type; /* Type of region */
+ __u64 base; /* Base address */
+ __u32 size; /* Size of region */
+ __u32 regnum; /* Register number */
+ __u32 type; /* Type of region */
+ __u32 _pad; /* Unused */
};
+
#endif /* !__i386__ */
struct mtrr_var_range {
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index bce688d54c1..e21fdd10479 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -55,7 +55,6 @@ extern unsigned long init_memory_mapping(unsigned long start,
unsigned long end);
extern void initmem_init(void);
-extern void free_initmem(void);
#endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cc4ad605c6f..aa0f9130836 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -10,6 +10,7 @@
#include <asm/paravirt_types.h>
#ifndef __ASSEMBLY__
+#include <linux/bug.h>
#include <linux/types.h>
#include <linux/cpumask.h>
@@ -230,9 +231,9 @@ static inline unsigned long long paravirt_sched_clock(void)
return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
}
-struct jump_label_key;
-extern struct jump_label_key paravirt_steal_enabled;
-extern struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
static inline u64 paravirt_steal_clock(int cpu)
{
@@ -298,12 +299,6 @@ static inline void set_ldt(const void *addr, unsigned entries)
{
PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries);
}
-#ifdef CONFIG_X86_32
-static inline void load_user_cs_desc(unsigned int cpu, struct mm_struct *mm)
-{
- PVOP_VCALL2(pv_cpu_ops.load_user_cs_desc, cpu, mm);
-}
-#endif /*CONFIG_X86_32*/
static inline void store_gdt(struct desc_ptr *dtr)
{
PVOP_VCALL1(pv_cpu_ops.store_gdt, dtr);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index cca421e9355..8e8b9a4987e 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -125,9 +125,6 @@ struct pv_cpu_ops {
void (*store_gdt)(struct desc_ptr *);
void (*store_idt)(struct desc_ptr *);
void (*set_ldt)(const void *desc, unsigned entries);
-#ifdef CONFIG_X86_32
- void (*load_user_cs_desc)(int cpu, struct mm_struct *mm);
-#endif
unsigned long (*store_tr)(void);
void (*load_tls)(struct thread_struct *t, unsigned int cpu);
#ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 461ce432b1c..2291895b183 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -23,6 +23,7 @@
#define ARCH_PERFMON_EVENTSEL_USR (1ULL << 16)
#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17)
#define ARCH_PERFMON_EVENTSEL_EDGE (1ULL << 18)
+#define ARCH_PERFMON_EVENTSEL_PIN_CONTROL (1ULL << 19)
#define ARCH_PERFMON_EVENTSEL_INT (1ULL << 20)
#define ARCH_PERFMON_EVENTSEL_ANY (1ULL << 21)
#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22)
@@ -188,8 +189,6 @@ extern u32 get_ibs_caps(void);
#ifdef CONFIG_PERF_EVENTS
extern void perf_events_lapic_init(void);
-#define PERF_EVENT_INDEX_OFFSET 0
-
/*
* Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups.
* This flag is otherwise unused and ABI specified to be 0, so nobody should
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index effff47a3c8..43876f16caf 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -31,6 +31,56 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte)
ptep->pte_low = pte.pte_low;
}
+#define pmd_read_atomic pmd_read_atomic
+/*
+ * pte_offset_map_lock on 32bit PAE kernels was reading the pmd_t with
+ * a "*pmdp" dereference done by gcc. Problem is, in certain places
+ * where pte_offset_map_lock is called, concurrent page faults are
+ * allowed, if the mmap_sem is hold for reading. An example is mincore
+ * vs page faults vs MADV_DONTNEED. On the page fault side
+ * pmd_populate rightfully does a set_64bit, but if we're reading the
+ * pmd_t with a "*pmdp" on the mincore side, a SMP race can happen
+ * because gcc will not read the 64bit of the pmd atomically. To fix
+ * this all places running pmd_offset_map_lock() while holding the
+ * mmap_sem in read mode, shall read the pmdp pointer using this
+ * function to know if the pmd is null nor not, and in turn to know if
+ * they can run pmd_offset_map_lock or pmd_trans_huge or other pmd
+ * operations.
+ *
+ * Without THP if the mmap_sem is hold for reading, the
+ * pmd can only transition from null to not null while pmd_read_atomic runs.
+ * So there's no need of literally reading it atomically.
+ *
+ * With THP if the mmap_sem is hold for reading, the pmd can become
+ * THP or null or point to a pte (and in turn become "stable") at any
+ * time under pmd_read_atomic, so it's mandatory to read it atomically
+ * with cmpxchg8b.
+ */
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+ pmdval_t ret;
+ u32 *tmp = (u32 *)pmdp;
+
+ ret = (pmdval_t) (*tmp);
+ if (ret) {
+ /*
+ * If the low part is null, we must not read the high part
+ * or we can end up with a partial pmd.
+ */
+ smp_rmb();
+ ret |= ((pmdval_t)*(tmp + 1)) << 32;
+ }
+
+ return (pmd_t) { ret };
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+ return (pmd_t) { atomic64_read((atomic64_t *)pmdp) };
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
{
set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h
index bb7133dc155..7ef7c3020e5 100644
--- a/arch/x86/include/asm/posix_types.h
+++ b/arch/x86/include/asm/posix_types.h
@@ -7,6 +7,8 @@
#else
# ifdef __i386__
# include "posix_types_32.h"
+# elif defined(__ILP32__)
+# include "posix_types_x32.h"
# else
# include "posix_types_64.h"
# endif
diff --git a/arch/x86/include/asm/posix_types_32.h b/arch/x86/include/asm/posix_types_32.h
index f7d9adf82e5..99f262e04b9 100644
--- a/arch/x86/include/asm/posix_types_32.h
+++ b/arch/x86/include/asm/posix_types_32.h
@@ -7,79 +7,22 @@
* assume GCC is being used.
*/
-typedef unsigned long __kernel_ino_t;
typedef unsigned short __kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
typedef unsigned short __kernel_nlink_t;
-typedef long __kernel_off_t;
-typedef int __kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
typedef unsigned short __kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
typedef unsigned short __kernel_uid_t;
typedef unsigned short __kernel_gid_t;
-typedef unsigned int __kernel_size_t;
-typedef int __kernel_ssize_t;
-typedef int __kernel_ptrdiff_t;
-typedef long __kernel_time_t;
-typedef long __kernel_suseconds_t;
-typedef long __kernel_clock_t;
-typedef int __kernel_timer_t;
-typedef int __kernel_clockid_t;
-typedef int __kernel_daddr_t;
-typedef char * __kernel_caddr_t;
-typedef unsigned short __kernel_uid16_t;
-typedef unsigned short __kernel_gid16_t;
-typedef unsigned int __kernel_uid32_t;
-typedef unsigned int __kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
-typedef unsigned short __kernel_old_uid_t;
-typedef unsigned short __kernel_old_gid_t;
typedef unsigned short __kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
-#ifdef __GNUC__
-typedef long long __kernel_loff_t;
-#endif
-
-typedef struct {
- int val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef __FD_SET
-#define __FD_SET(fd,fdsetp) \
- asm volatile("btsl %1,%0": \
- "+m" (*(__kernel_fd_set *)(fdsetp)) \
- : "r" ((int)(fd)))
-
-#undef __FD_CLR
-#define __FD_CLR(fd,fdsetp) \
- asm volatile("btrl %1,%0": \
- "+m" (*(__kernel_fd_set *)(fdsetp)) \
- : "r" ((int) (fd)))
-
-#undef __FD_ISSET
-#define __FD_ISSET(fd,fdsetp) \
- (__extension__ \
- ({ \
- unsigned char __result; \
- asm volatile("btl %1,%2 ; setb %0" \
- : "=q" (__result) \
- : "r" ((int)(fd)), \
- "m" (*(__kernel_fd_set *)(fdsetp))); \
- __result; \
-}))
-
-#undef __FD_ZERO
-#define __FD_ZERO(fdsetp) \
-do { \
- int __d0, __d1; \
- asm volatile("cld ; rep ; stosl" \
- : "=m" (*(__kernel_fd_set *)(fdsetp)), \
- "=&c" (__d0), "=&D" (__d1) \
- : "a" (0), "1" (__FDSET_LONGS), \
- "2" ((__kernel_fd_set *)(fdsetp)) \
- : "memory"); \
-} while (0)
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
#endif /* _ASM_X86_POSIX_TYPES_32_H */
diff --git a/arch/x86/include/asm/posix_types_64.h b/arch/x86/include/asm/posix_types_64.h
index eb8d2d92b63..cba0c1ead16 100644
--- a/arch/x86/include/asm/posix_types_64.h
+++ b/arch/x86/include/asm/posix_types_64.h
@@ -7,113 +7,13 @@
* assume GCC is being used.
*/
-typedef unsigned long __kernel_ino_t;
-typedef unsigned int __kernel_mode_t;
-typedef unsigned long __kernel_nlink_t;
-typedef long __kernel_off_t;
-typedef int __kernel_pid_t;
-typedef int __kernel_ipc_pid_t;
-typedef unsigned int __kernel_uid_t;
-typedef unsigned int __kernel_gid_t;
-typedef unsigned long __kernel_size_t;
-typedef long __kernel_ssize_t;
-typedef long __kernel_ptrdiff_t;
-typedef long __kernel_time_t;
-typedef long __kernel_suseconds_t;
-typedef long __kernel_clock_t;
-typedef int __kernel_timer_t;
-typedef int __kernel_clockid_t;
-typedef int __kernel_daddr_t;
-typedef char * __kernel_caddr_t;
-typedef unsigned short __kernel_uid16_t;
-typedef unsigned short __kernel_gid16_t;
-
-#ifdef __GNUC__
-typedef long long __kernel_loff_t;
-#endif
-
-typedef struct {
- int val[2];
-} __kernel_fsid_t;
-
typedef unsigned short __kernel_old_uid_t;
typedef unsigned short __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
typedef unsigned long __kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
- unsigned long _tmp = fd / __NFDBITS;
- unsigned long _rem = fd % __NFDBITS;
- fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
- unsigned long _tmp = fd / __NFDBITS;
- unsigned long _rem = fd % __NFDBITS;
- fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p)
-{
- unsigned long _tmp = fd / __NFDBITS;
- unsigned long _rem = fd % __NFDBITS;
- return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant cases (8 or 32 longs,
- * for 256 and 1024-bit fd_sets respectively)
- */
-#undef __FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *p)
-{
- unsigned long *tmp = p->fds_bits;
- int i;
-
- if (__builtin_constant_p(__FDSET_LONGS)) {
- switch (__FDSET_LONGS) {
- case 32:
- tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
- tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
- tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
- tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
- tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0;
- tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0;
- tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0;
- tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0;
- return;
- case 16:
- tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
- tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
- tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
- tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
- return;
- case 8:
- tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
- tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
- return;
- case 4:
- tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
- return;
- }
- }
- i = __FDSET_LONGS;
- while (i) {
- i--;
- *tmp = 0;
- tmp++;
- }
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
#endif /* _ASM_X86_POSIX_TYPES_64_H */
diff --git a/arch/x86/include/asm/posix_types_x32.h b/arch/x86/include/asm/posix_types_x32.h
new file mode 100644
index 00000000000..85f9bdafa93
--- /dev/null
+++ b/arch/x86/include/asm/posix_types_x32.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_X86_POSIX_TYPES_X32_H
+#define _ASM_X86_POSIX_TYPES_X32_H
+
+/*
+ * This file is only used by user-level software, so you need to
+ * be a little careful about namespace pollution etc. Also, we cannot
+ * assume GCC is being used.
+ *
+ * These types should generally match the ones used by the 64-bit kernel,
+ *
+ */
+
+typedef long long __kernel_long_t;
+typedef unsigned long long __kernel_ulong_t;
+#define __kernel_long_t __kernel_long_t
+
+#include <asm/posix_types_64.h>
+
+#endif /* _ASM_X86_POSIX_TYPES_X32_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 58545c97d07..4fa7dcceb6c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -14,13 +14,13 @@ struct mm_struct;
#include <asm/sigcontext.h>
#include <asm/current.h>
#include <asm/cpufeature.h>
-#include <asm/system.h>
#include <asm/page.h>
#include <asm/pgtable_types.h>
#include <asm/percpu.h>
#include <asm/msr.h>
#include <asm/desc_defs.h>
#include <asm/nops.h>
+#include <asm/special_insns.h>
#include <linux/personality.h>
#include <linux/cpumask.h>
@@ -29,6 +29,15 @@ struct mm_struct;
#include <linux/math64.h>
#include <linux/init.h>
#include <linux/err.h>
+#include <linux/irqflags.h>
+
+/*
+ * We handle most unaligned accesses in hardware. On the other hand
+ * unaligned DMA can be quite expensive on some Nehalem processors.
+ *
+ * Based on this we disable the IP header alignment in network drivers.
+ */
+#define NET_IP_ALIGN 0
#define HBP_NUM 4
/*
@@ -162,6 +171,7 @@ extern void early_cpu_init(void);
extern void identify_boot_cpu(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
+void print_cpu_msr(struct cpuinfo_x86 *);
extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
extern unsigned short num_cache_leaves;
@@ -453,7 +463,7 @@ struct thread_struct {
unsigned long ptrace_dr7;
/* Fault info: */
unsigned long cr2;
- unsigned long trap_no;
+ unsigned long trap_nr;
unsigned long error_code;
/* floating point and extended processor state */
struct fpu fpu;
@@ -474,61 +484,6 @@ struct thread_struct {
unsigned io_bitmap_max;
};
-static inline unsigned long native_get_debugreg(int regno)
-{
- unsigned long val = 0; /* Damn you, gcc! */
-
- switch (regno) {
- case 0:
- asm("mov %%db0, %0" :"=r" (val));
- break;
- case 1:
- asm("mov %%db1, %0" :"=r" (val));
- break;
- case 2:
- asm("mov %%db2, %0" :"=r" (val));
- break;
- case 3:
- asm("mov %%db3, %0" :"=r" (val));
- break;
- case 6:
- asm("mov %%db6, %0" :"=r" (val));
- break;
- case 7:
- asm("mov %%db7, %0" :"=r" (val));
- break;
- default:
- BUG();
- }
- return val;
-}
-
-static inline void native_set_debugreg(int regno, unsigned long value)
-{
- switch (regno) {
- case 0:
- asm("mov %0, %%db0" ::"r" (value));
- break;
- case 1:
- asm("mov %0, %%db1" ::"r" (value));
- break;
- case 2:
- asm("mov %0, %%db2" ::"r" (value));
- break;
- case 3:
- asm("mov %0, %%db3" ::"r" (value));
- break;
- case 6:
- asm("mov %0, %%db6" ::"r" (value));
- break;
- case 7:
- asm("mov %0, %%db7" ::"r" (value));
- break;
- default:
- BUG();
- }
-}
-
/*
* Set IOPL bits in EFLAGS from given mask
*/
@@ -574,14 +529,6 @@ static inline void native_swapgs(void)
#define __cpuid native_cpuid
#define paravirt_enabled() 0
-/*
- * These special macros can be used to get or set a debugging register
- */
-#define get_debugreg(var, register) \
- (var) = native_get_debugreg(register)
-#define set_debugreg(value, register) \
- native_set_debugreg(register, value)
-
static inline void load_sp0(struct tss_struct *tss,
struct thread_struct *thread)
{
@@ -926,9 +873,9 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
#define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \
0xc0000000 : 0xFFFFe000)
-#define TASK_SIZE (test_thread_flag(TIF_IA32) ? \
+#define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \
IA32_PAGE_OFFSET : TASK_SIZE_MAX)
-#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_IA32)) ? \
+#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
IA32_PAGE_OFFSET : TASK_SIZE_MAX)
#define STACK_TOP TASK_SIZE
@@ -950,6 +897,12 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1)
extern unsigned long KSTK_ESP(struct task_struct *task);
+
+/*
+ * User space RSP while inside the SYSCALL fast path
+ */
+DECLARE_PER_CPU(unsigned long, old_rsp);
+
#endif /* CONFIG_X86_64 */
extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
@@ -1021,4 +974,14 @@ extern bool cpu_has_amd_erratum(const int *);
#define cpu_has_amd_erratum(x) (false)
#endif /* CONFIG_CPU_SUP_AMD */
+void cpu_idle_wait(void);
+
+extern unsigned long arch_align_stack(unsigned long sp);
+extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+
+void default_idle(void);
+bool set_pm_idle_to_default(void);
+
+void stop_this_cpu(void *dummy);
+
#endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index 644dd885f05..60bef663609 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -21,7 +21,6 @@
#include <asm/irq.h>
#include <linux/atomic.h>
#include <asm/setup.h>
-#include <asm/irq_controller.h>
#ifdef CONFIG_OF
extern int of_ioapic;
@@ -43,15 +42,6 @@ extern char cmd_line[COMMAND_LINE_SIZE];
#define pci_address_to_pio pci_address_to_pio
unsigned long pci_address_to_pio(phys_addr_t addr);
-/**
- * irq_dispose_mapping - Unmap an interrupt
- * @virq: linux virq number of the interrupt to unmap
- *
- * FIXME: We really should implement proper virq handling like power,
- * but that's going to be major surgery.
- */
-static inline void irq_dispose_mapping(unsigned int virq) { }
-
#define HAVE_ARCH_DEVTREE_FIXUPS
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 35664547125..dcfde52979c 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -145,7 +145,6 @@ extern unsigned long
convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
int error_code, int si_code);
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
extern long syscall_trace_enter(struct pt_regs *);
extern void syscall_trace_leave(struct pt_regs *);
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 5e641715c3f..165466233ab 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -212,7 +212,61 @@
#ifdef __KERNEL__
#ifndef __ASSEMBLY__
extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10];
-#endif
-#endif
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg, value) \
+do { \
+ unsigned short __val = (value); \
+ \
+ asm volatile(" \n" \
+ "1: movl %k0,%%" #seg " \n" \
+ \
+ ".section .fixup,\"ax\" \n" \
+ "2: xorl %k0,%k0 \n" \
+ " jmp 1b \n" \
+ ".previous \n" \
+ \
+ _ASM_EXTABLE(1b, 2b) \
+ \
+ : "+r" (__val) : : "memory"); \
+} while (0)
+
+/*
+ * Save a segment register away
+ */
+#define savesegment(seg, value) \
+ asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
+
+/*
+ * x86_32 user gs accessors.
+ */
+#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_32_LAZY_GS
+#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;})
+#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v))
+#define task_user_gs(tsk) ((tsk)->thread.gs)
+#define lazy_save_gs(v) savesegment(gs, (v))
+#define lazy_load_gs(v) loadsegment(gs, (v))
+#else /* X86_32_LAZY_GS */
+#define get_user_gs(regs) (u16)((regs)->gs)
+#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0)
+#define task_user_gs(tsk) (task_pt_regs(tsk)->gs)
+#define lazy_save_gs(v) do { } while (0)
+#define lazy_load_gs(v) do { } while (0)
+#endif /* X86_32_LAZY_GS */
+#endif /* X86_32 */
+
+static inline unsigned long get_limit(unsigned long segment)
+{
+ unsigned long __limit;
+ asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
+ return __limit + 1;
+}
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __KERNEL__ */
#endif /* _ASM_X86_SEGMENT_H */
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 04459d25e66..5ca71c065ee 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -230,34 +230,37 @@ struct sigcontext {
* User-space might still rely on the old definition:
*/
struct sigcontext {
- unsigned long r8;
- unsigned long r9;
- unsigned long r10;
- unsigned long r11;
- unsigned long r12;
- unsigned long r13;
- unsigned long r14;
- unsigned long r15;
- unsigned long rdi;
- unsigned long rsi;
- unsigned long rbp;
- unsigned long rbx;
- unsigned long rdx;
- unsigned long rax;
- unsigned long rcx;
- unsigned long rsp;
- unsigned long rip;
- unsigned long eflags; /* RFLAGS */
- unsigned short cs;
- unsigned short gs;
- unsigned short fs;
- unsigned short __pad0;
- unsigned long err;
- unsigned long trapno;
- unsigned long oldmask;
- unsigned long cr2;
+ __u64 r8;
+ __u64 r9;
+ __u64 r10;
+ __u64 r11;
+ __u64 r12;
+ __u64 r13;
+ __u64 r14;
+ __u64 r15;
+ __u64 rdi;
+ __u64 rsi;
+ __u64 rbp;
+ __u64 rbx;
+ __u64 rdx;
+ __u64 rax;
+ __u64 rcx;
+ __u64 rsp;
+ __u64 rip;
+ __u64 eflags; /* RFLAGS */
+ __u16 cs;
+ __u16 gs;
+ __u16 fs;
+ __u16 __pad0;
+ __u64 err;
+ __u64 trapno;
+ __u64 oldmask;
+ __u64 cr2;
struct _fpstate __user *fpstate; /* zero when no FPU context */
- unsigned long reserved1[8];
+#ifdef __ILP32__
+ __u32 __fpstate_pad;
+#endif
+ __u64 reserved1[8];
};
#endif /* !__KERNEL__ */
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
index 4e0fe26d27d..7c7c27c97da 100644
--- a/arch/x86/include/asm/sigframe.h
+++ b/arch/x86/include/asm/sigframe.h
@@ -59,12 +59,25 @@ struct rt_sigframe_ia32 {
#endif /* defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) */
#ifdef CONFIG_X86_64
+
struct rt_sigframe {
char __user *pretcode;
struct ucontext uc;
struct siginfo info;
/* fp state follows here */
};
+
+#ifdef CONFIG_X86_X32_ABI
+
+struct rt_sigframe_x32 {
+ u64 pretcode;
+ struct ucontext_x32 uc;
+ compat_siginfo_t info;
+ /* fp state follows here */
+};
+
+#endif /* CONFIG_X86_X32_ABI */
+
#endif /* CONFIG_X86_64 */
#endif /* _ASM_X86_SIGFRAME_H */
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
new file mode 100644
index 00000000000..ada93b3b8c6
--- /dev/null
+++ b/arch/x86/include/asm/sighandling.h
@@ -0,0 +1,24 @@
+#ifndef _ASM_X86_SIGHANDLING_H
+#define _ASM_X86_SIGHANDLING_H
+
+#include <linux/compiler.h>
+#include <linux/ptrace.h>
+#include <linux/signal.h>
+
+#include <asm/processor-flags.h>
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+#define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \
+ X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
+ X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
+ X86_EFLAGS_CF)
+
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+
+int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
+ unsigned long *pax);
+int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
+ struct pt_regs *regs, unsigned long mask);
+
+#endif /* _ASM_X86_SIGHANDLING_H */
diff --git a/arch/x86/include/asm/siginfo.h b/arch/x86/include/asm/siginfo.h
index fc1aa553564..34c47b3341c 100644
--- a/arch/x86/include/asm/siginfo.h
+++ b/arch/x86/include/asm/siginfo.h
@@ -2,7 +2,13 @@
#define _ASM_X86_SIGINFO_H
#ifdef __x86_64__
-# define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int))
+# ifdef __ILP32__ /* x32 */
+typedef long long __kernel_si_clock_t __attribute__((aligned(4)));
+# define __ARCH_SI_CLOCK_T __kernel_si_clock_t
+# define __ARCH_SI_ATTRIBUTES __attribute__((aligned(8)))
+# else /* x86-64 */
+# define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int))
+# endif
#endif
#include <asm-generic/siginfo.h>
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
new file mode 100644
index 00000000000..41fc93a2e22
--- /dev/null
+++ b/arch/x86/include/asm/special_insns.h
@@ -0,0 +1,199 @@
+#ifndef _ASM_X86_SPECIAL_INSNS_H
+#define _ASM_X86_SPECIAL_INSNS_H
+
+
+#ifdef __KERNEL__
+
+static inline void native_clts(void)
+{
+ asm volatile("clts");
+}
+
+/*
+ * Volatile isn't enough to prevent the compiler from reordering the
+ * read/write functions for the control registers and messing everything up.
+ * A memory clobber would solve the problem, but would prevent reordering of
+ * all loads stores around it, which can hurt performance. Solution is to
+ * use a variable and mimic reads and writes to it to enforce serialization
+ */
+static unsigned long __force_order;
+
+static inline unsigned long native_read_cr0(void)
+{
+ unsigned long val;
+ asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
+ return val;
+}
+
+static inline void native_write_cr0(unsigned long val)
+{
+ asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr2(void)
+{
+ unsigned long val;
+ asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
+ return val;
+}
+
+static inline void native_write_cr2(unsigned long val)
+{
+ asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr3(void)
+{
+ unsigned long val;
+ asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
+ return val;
+}
+
+static inline void native_write_cr3(unsigned long val)
+{
+ asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr4(void)
+{
+ unsigned long val;
+ asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
+ return val;
+}
+
+static inline unsigned long native_read_cr4_safe(void)
+{
+ unsigned long val;
+ /* This could fault if %cr4 does not exist. In x86_64, a cr4 always
+ * exists, so it will never fail. */
+#ifdef CONFIG_X86_32
+ asm volatile("1: mov %%cr4, %0\n"
+ "2:\n"
+ _ASM_EXTABLE(1b, 2b)
+ : "=r" (val), "=m" (__force_order) : "0" (0));
+#else
+ val = native_read_cr4();
+#endif
+ return val;
+}
+
+static inline void native_write_cr4(unsigned long val)
+{
+ asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
+}
+
+#ifdef CONFIG_X86_64
+static inline unsigned long native_read_cr8(void)
+{
+ unsigned long cr8;
+ asm volatile("movq %%cr8,%0" : "=r" (cr8));
+ return cr8;
+}
+
+static inline void native_write_cr8(unsigned long val)
+{
+ asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
+}
+#endif
+
+static inline void native_wbinvd(void)
+{
+ asm volatile("wbinvd": : :"memory");
+}
+
+extern void native_load_gs_index(unsigned);
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+
+static inline unsigned long read_cr0(void)
+{
+ return native_read_cr0();
+}
+
+static inline void write_cr0(unsigned long x)
+{
+ native_write_cr0(x);
+}
+
+static inline unsigned long read_cr2(void)
+{
+ return native_read_cr2();
+}
+
+static inline void write_cr2(unsigned long x)
+{
+ native_write_cr2(x);
+}
+
+static inline unsigned long read_cr3(void)
+{
+ return native_read_cr3();
+}
+
+static inline void write_cr3(unsigned long x)
+{
+ native_write_cr3(x);
+}
+
+static inline unsigned long read_cr4(void)
+{
+ return native_read_cr4();
+}
+
+static inline unsigned long read_cr4_safe(void)
+{
+ return native_read_cr4_safe();
+}
+
+static inline void write_cr4(unsigned long x)
+{
+ native_write_cr4(x);
+}
+
+static inline void wbinvd(void)
+{
+ native_wbinvd();
+}
+
+#ifdef CONFIG_X86_64
+
+static inline unsigned long read_cr8(void)
+{
+ return native_read_cr8();
+}
+
+static inline void write_cr8(unsigned long x)
+{
+ native_write_cr8(x);
+}
+
+static inline void load_gs_index(unsigned selector)
+{
+ native_load_gs_index(selector);
+}
+
+#endif
+
+/* Clear the 'TS' bit */
+static inline void clts(void)
+{
+ native_clts();
+}
+
+#endif/* CONFIG_PARAVIRT */
+
+#define stts() write_cr0(read_cr0() | X86_CR0_TS)
+
+static inline void clflush(volatile void *__p)
+{
+ asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
+}
+
+#define nop() asm volatile ("nop")
+
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index a82c2bf504b..76bfa2cf301 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -88,14 +88,14 @@ static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
{
struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
- return !!(tmp.tail ^ tmp.head);
+ return tmp.tail != tmp.head;
}
static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
{
struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
- return ((tmp.tail - tmp.head) & TICKET_MASK) > 1;
+ return (__ticket_t)(tmp.tail - tmp.head) > 1;
}
#ifndef CONFIG_PARAVIRT_SPINLOCKS
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 8ebd5df7451..ad0ad07fc00 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -16,7 +16,6 @@ typedef u32 __ticketpair_t;
#endif
#define TICKET_SHIFT (sizeof(__ticket_t) * 8)
-#define TICKET_MASK ((__ticket_t)((1 << TICKET_SHIFT) - 1))
typedef struct arch_spinlock {
union {
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 15751776356..b5d9533d2c3 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -38,7 +38,6 @@
#include <asm/tsc.h>
#include <asm/processor.h>
#include <asm/percpu.h>
-#include <asm/system.h>
#include <asm/desc.h>
#include <linux/random.h>
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
new file mode 100644
index 00000000000..4ec45b3abba
--- /dev/null
+++ b/arch/x86/include/asm/switch_to.h
@@ -0,0 +1,129 @@
+#ifndef _ASM_X86_SWITCH_TO_H
+#define _ASM_X86_SWITCH_TO_H
+
+struct task_struct; /* one of the stranger aspects of C forward declarations */
+struct task_struct *__switch_to(struct task_struct *prev,
+ struct task_struct *next);
+struct tss_struct;
+void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
+ struct tss_struct *tss);
+
+#ifdef CONFIG_X86_32
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary \
+ "movl %P[task_canary](%[next]), %%ebx\n\t" \
+ "movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
+#define __switch_canary_oparam \
+ , [stack_canary] "=m" (stack_canary.canary)
+#define __switch_canary_iparam \
+ , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else /* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif /* CC_STACKPROTECTOR */
+
+/*
+ * Saving eflags is important. It switches not only IOPL between tasks,
+ * it also protects other tasks from NT leaking through sysenter etc.
+ */
+#define switch_to(prev, next, last) \
+do { \
+ /* \
+ * Context-switching clobbers all registers, so we clobber \
+ * them explicitly, via unused output variables. \
+ * (EAX and EBP is not listed because EBP is saved/restored \
+ * explicitly for wchan access and EAX is the return value of \
+ * __switch_to()) \
+ */ \
+ unsigned long ebx, ecx, edx, esi, edi; \
+ \
+ asm volatile("pushfl\n\t" /* save flags */ \
+ "pushl %%ebp\n\t" /* save EBP */ \
+ "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \
+ "movl %[next_sp],%%esp\n\t" /* restore ESP */ \
+ "movl $1f,%[prev_ip]\n\t" /* save EIP */ \
+ "pushl %[next_ip]\n\t" /* restore EIP */ \
+ __switch_canary \
+ "jmp __switch_to\n" /* regparm call */ \
+ "1:\t" \
+ "popl %%ebp\n\t" /* restore EBP */ \
+ "popfl\n" /* restore flags */ \
+ \
+ /* output parameters */ \
+ : [prev_sp] "=m" (prev->thread.sp), \
+ [prev_ip] "=m" (prev->thread.ip), \
+ "=a" (last), \
+ \
+ /* clobbered output registers: */ \
+ "=b" (ebx), "=c" (ecx), "=d" (edx), \
+ "=S" (esi), "=D" (edi) \
+ \
+ __switch_canary_oparam \
+ \
+ /* input parameters: */ \
+ : [next_sp] "m" (next->thread.sp), \
+ [next_ip] "m" (next->thread.ip), \
+ \
+ /* regparm parameters for __switch_to(): */ \
+ [prev] "a" (prev), \
+ [next] "d" (next) \
+ \
+ __switch_canary_iparam \
+ \
+ : /* reloaded segment registers */ \
+ "memory"); \
+} while (0)
+
+#else /* CONFIG_X86_32 */
+
+/* frame pointer must be last for get_wchan */
+#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
+
+#define __EXTRA_CLOBBER \
+ , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
+ "r12", "r13", "r14", "r15"
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary \
+ "movq %P[task_canary](%%rsi),%%r8\n\t" \
+ "movq %%r8,"__percpu_arg([gs_canary])"\n\t"
+#define __switch_canary_oparam \
+ , [gs_canary] "=m" (irq_stack_union.stack_canary)
+#define __switch_canary_iparam \
+ , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else /* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif /* CC_STACKPROTECTOR */
+
+/* Save restore flags to clear handle leaking NT */
+#define switch_to(prev, next, last) \
+ asm volatile(SAVE_CONTEXT \
+ "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \
+ "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \
+ "call __switch_to\n\t" \
+ "movq "__percpu_arg([current_task])",%%rsi\n\t" \
+ __switch_canary \
+ "movq %P[thread_info](%%rsi),%%r8\n\t" \
+ "movq %%rax,%%rdi\n\t" \
+ "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \
+ "jnz ret_from_fork\n\t" \
+ RESTORE_CONTEXT \
+ : "=a" (last) \
+ __switch_canary_oparam \
+ : [next] "S" (next), [prev] "D" (prev), \
+ [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
+ [ti_flags] "i" (offsetof(struct thread_info, flags)), \
+ [_tif_fork] "i" (_TIF_FORK), \
+ [thread_info] "i" (offsetof(struct task_struct, stack)), \
+ [current_task] "m" (current_task) \
+ __switch_canary_iparam \
+ : "memory", "cc" __EXTRA_CLOBBER)
+
+#endif /* CONFIG_X86_32 */
+
+#endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index cb238526a9f..3fda9db4881 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -10,6 +10,8 @@
#ifndef _ASM_X86_SYS_IA32_H
#define _ASM_X86_SYS_IA32_H
+#ifdef CONFIG_COMPAT
+
#include <linux/compiler.h>
#include <linux/linkage.h>
#include <linux/types.h>
@@ -36,8 +38,6 @@ asmlinkage long sys32_rt_sigaction(int, struct sigaction32 __user *,
struct sigaction32 __user *, unsigned int);
asmlinkage long sys32_sigaction(int, struct old_sigaction32 __user *,
struct old_sigaction32 __user *);
-asmlinkage long sys32_rt_sigprocmask(int, compat_sigset_t __user *,
- compat_sigset_t __user *, unsigned int);
asmlinkage long sys32_alarm(unsigned int);
asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int);
@@ -83,4 +83,7 @@ asmlinkage long sys32_ipc(u32, int, int, int, compat_uptr_t, u32);
asmlinkage long sys32_fanotify_mark(int, unsigned int, u32, u32, int,
const char __user *);
+
+#endif /* CONFIG_COMPAT */
+
#endif /* _ASM_X86_SYS_IA32_H */
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d962e5652a7..386b78686c4 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,6 +16,7 @@
#include <linux/sched.h>
#include <linux/err.h>
#include <asm/asm-offsets.h> /* For NR_syscalls */
+#include <asm/unistd.h>
extern const unsigned long sys_call_table[];
@@ -26,13 +27,13 @@ extern const unsigned long sys_call_table[];
*/
static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
{
- return regs->orig_ax;
+ return regs->orig_ax & __SYSCALL_MASK;
}
static inline void syscall_rollback(struct task_struct *task,
struct pt_regs *regs)
{
- regs->ax = regs->orig_ax;
+ regs->ax = regs->orig_ax & __SYSCALL_MASK;
}
static inline long syscall_get_error(struct task_struct *task,
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
deleted file mode 100644
index 2d2f01ce6dc..00000000000
--- a/arch/x86/include/asm/system.h
+++ /dev/null
@@ -1,523 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_H
-#define _ASM_X86_SYSTEM_H
-
-#include <asm/asm.h>
-#include <asm/segment.h>
-#include <asm/cpufeature.h>
-#include <asm/cmpxchg.h>
-#include <asm/nops.h>
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-/* entries in ARCH_DLINFO: */
-#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
-# define AT_VECTOR_SIZE_ARCH 2
-#else /* else it's non-compat x86-64 */
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-struct task_struct; /* one of the stranger aspects of C forward declarations */
-struct task_struct *__switch_to(struct task_struct *prev,
- struct task_struct *next);
-struct tss_struct;
-void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
- struct tss_struct *tss);
-extern void show_regs_common(void);
-
-#ifdef CONFIG_X86_32
-
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary \
- "movl %P[task_canary](%[next]), %%ebx\n\t" \
- "movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
-#define __switch_canary_oparam \
- , [stack_canary] "=m" (stack_canary.canary)
-#define __switch_canary_iparam \
- , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else /* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif /* CC_STACKPROTECTOR */
-
-/*
- * Saving eflags is important. It switches not only IOPL between tasks,
- * it also protects other tasks from NT leaking through sysenter etc.
- */
-#define switch_to(prev, next, last) \
-do { \
- /* \
- * Context-switching clobbers all registers, so we clobber \
- * them explicitly, via unused output variables. \
- * (EAX and EBP is not listed because EBP is saved/restored \
- * explicitly for wchan access and EAX is the return value of \
- * __switch_to()) \
- */ \
- unsigned long ebx, ecx, edx, esi, edi; \
- \
- asm volatile("pushfl\n\t" /* save flags */ \
- "pushl %%ebp\n\t" /* save EBP */ \
- "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \
- "movl %[next_sp],%%esp\n\t" /* restore ESP */ \
- "movl $1f,%[prev_ip]\n\t" /* save EIP */ \
- "pushl %[next_ip]\n\t" /* restore EIP */ \
- __switch_canary \
- "jmp __switch_to\n" /* regparm call */ \
- "1:\t" \
- "popl %%ebp\n\t" /* restore EBP */ \
- "popfl\n" /* restore flags */ \
- \
- /* output parameters */ \
- : [prev_sp] "=m" (prev->thread.sp), \
- [prev_ip] "=m" (prev->thread.ip), \
- "=a" (last), \
- \
- /* clobbered output registers: */ \
- "=b" (ebx), "=c" (ecx), "=d" (edx), \
- "=S" (esi), "=D" (edi) \
- \
- __switch_canary_oparam \
- \
- /* input parameters: */ \
- : [next_sp] "m" (next->thread.sp), \
- [next_ip] "m" (next->thread.ip), \
- \
- /* regparm parameters for __switch_to(): */ \
- [prev] "a" (prev), \
- [next] "d" (next) \
- \
- __switch_canary_iparam \
- \
- : /* reloaded segment registers */ \
- "memory"); \
-} while (0)
-
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-#else
-
-/* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
-
-#define __EXTRA_CLOBBER \
- , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
- "r12", "r13", "r14", "r15"
-
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary \
- "movq %P[task_canary](%%rsi),%%r8\n\t" \
- "movq %%r8,"__percpu_arg([gs_canary])"\n\t"
-#define __switch_canary_oparam \
- , [gs_canary] "=m" (irq_stack_union.stack_canary)
-#define __switch_canary_iparam \
- , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else /* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif /* CC_STACKPROTECTOR */
-
-/* Save restore flags to clear handle leaking NT */
-#define switch_to(prev, next, last) \
- asm volatile(SAVE_CONTEXT \
- "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \
- "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \
- "call __switch_to\n\t" \
- "movq "__percpu_arg([current_task])",%%rsi\n\t" \
- __switch_canary \
- "movq %P[thread_info](%%rsi),%%r8\n\t" \
- "movq %%rax,%%rdi\n\t" \
- "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \
- "jnz ret_from_fork\n\t" \
- RESTORE_CONTEXT \
- : "=a" (last) \
- __switch_canary_oparam \
- : [next] "S" (next), [prev] "D" (prev), \
- [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
- [ti_flags] "i" (offsetof(struct thread_info, flags)), \
- [_tif_fork] "i" (_TIF_FORK), \
- [thread_info] "i" (offsetof(struct task_struct, stack)), \
- [current_task] "m" (current_task) \
- __switch_canary_iparam \
- : "memory", "cc" __EXTRA_CLOBBER)
-#endif
-
-#ifdef __KERNEL__
-
-extern void native_load_gs_index(unsigned);
-
-/*
- * Load a segment. Fall back on loading the zero
- * segment if something goes wrong..
- */
-#define loadsegment(seg, value) \
-do { \
- unsigned short __val = (value); \
- \
- asm volatile(" \n" \
- "1: movl %k0,%%" #seg " \n" \
- \
- ".section .fixup,\"ax\" \n" \
- "2: xorl %k0,%k0 \n" \
- " jmp 1b \n" \
- ".previous \n" \
- \
- _ASM_EXTABLE(1b, 2b) \
- \
- : "+r" (__val) : : "memory"); \
-} while (0)
-
-/*
- * Save a segment register away
- */
-#define savesegment(seg, value) \
- asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
-
-/*
- * x86_32 user gs accessors.
- */
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_X86_32_LAZY_GS
-#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;})
-#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v))
-#define task_user_gs(tsk) ((tsk)->thread.gs)
-#define lazy_save_gs(v) savesegment(gs, (v))
-#define lazy_load_gs(v) loadsegment(gs, (v))
-#else /* X86_32_LAZY_GS */
-#define get_user_gs(regs) (u16)((regs)->gs)
-#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0)
-#define task_user_gs(tsk) (task_pt_regs(tsk)->gs)
-#define lazy_save_gs(v) do { } while (0)
-#define lazy_load_gs(v) do { } while (0)
-#endif /* X86_32_LAZY_GS */
-#endif /* X86_32 */
-
-static inline unsigned long get_limit(unsigned long segment)
-{
- unsigned long __limit;
- asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
- return __limit + 1;
-}
-
-static inline void native_clts(void)
-{
- asm volatile("clts");
-}
-
-/*
- * Volatile isn't enough to prevent the compiler from reordering the
- * read/write functions for the control registers and messing everything up.
- * A memory clobber would solve the problem, but would prevent reordering of
- * all loads stores around it, which can hurt performance. Solution is to
- * use a variable and mimic reads and writes to it to enforce serialization
- */
-static unsigned long __force_order;
-
-static inline unsigned long native_read_cr0(void)
-{
- unsigned long val;
- asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
- return val;
-}
-
-static inline void native_write_cr0(unsigned long val)
-{
- asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr2(void)
-{
- unsigned long val;
- asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
- return val;
-}
-
-static inline void native_write_cr2(unsigned long val)
-{
- asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr3(void)
-{
- unsigned long val;
- asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
- return val;
-}
-
-static inline void native_write_cr3(unsigned long val)
-{
- asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr4(void)
-{
- unsigned long val;
- asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
- return val;
-}
-
-static inline unsigned long native_read_cr4_safe(void)
-{
- unsigned long val;
- /* This could fault if %cr4 does not exist. In x86_64, a cr4 always
- * exists, so it will never fail. */
-#ifdef CONFIG_X86_32
- asm volatile("1: mov %%cr4, %0\n"
- "2:\n"
- _ASM_EXTABLE(1b, 2b)
- : "=r" (val), "=m" (__force_order) : "0" (0));
-#else
- val = native_read_cr4();
-#endif
- return val;
-}
-
-static inline void native_write_cr4(unsigned long val)
-{
- asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
-}
-
-#ifdef CONFIG_X86_64
-static inline unsigned long native_read_cr8(void)
-{
- unsigned long cr8;
- asm volatile("movq %%cr8,%0" : "=r" (cr8));
- return cr8;
-}
-
-static inline void native_write_cr8(unsigned long val)
-{
- asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
-}
-#endif
-
-static inline void native_wbinvd(void)
-{
- asm volatile("wbinvd": : :"memory");
-}
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-
-static inline unsigned long read_cr0(void)
-{
- return native_read_cr0();
-}
-
-static inline void write_cr0(unsigned long x)
-{
- native_write_cr0(x);
-}
-
-static inline unsigned long read_cr2(void)
-{
- return native_read_cr2();
-}
-
-static inline void write_cr2(unsigned long x)
-{
- native_write_cr2(x);
-}
-
-static inline unsigned long read_cr3(void)
-{
- return native_read_cr3();
-}
-
-static inline void write_cr3(unsigned long x)
-{
- native_write_cr3(x);
-}
-
-static inline unsigned long read_cr4(void)
-{
- return native_read_cr4();
-}
-
-static inline unsigned long read_cr4_safe(void)
-{
- return native_read_cr4_safe();
-}
-
-static inline void write_cr4(unsigned long x)
-{
- native_write_cr4(x);
-}
-
-static inline void wbinvd(void)
-{
- native_wbinvd();
-}
-
-#ifdef CONFIG_X86_64
-
-static inline unsigned long read_cr8(void)
-{
- return native_read_cr8();
-}
-
-static inline void write_cr8(unsigned long x)
-{
- native_write_cr8(x);
-}
-
-static inline void load_gs_index(unsigned selector)
-{
- native_load_gs_index(selector);
-}
-
-#endif
-
-/* Clear the 'TS' bit */
-static inline void clts(void)
-{
- native_clts();
-}
-
-#endif/* CONFIG_PARAVIRT */
-
-#define stts() write_cr0(read_cr0() | X86_CR0_TS)
-
-#endif /* __KERNEL__ */
-
-static inline void clflush(volatile void *__p)
-{
- asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
-}
-
-#define nop() asm volatile ("nop")
-
-void disable_hlt(void);
-void enable_hlt(void);
-
-void cpu_idle_wait(void);
-
-extern unsigned long arch_align_stack(unsigned long sp);
-extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
-
-void default_idle(void);
-bool set_pm_idle_to_default(void);
-
-void stop_this_cpu(void *dummy);
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- */
-#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define mb() asm volatile("mfence":::"memory")
-#define rmb() asm volatile("lfence":::"memory")
-#define wmb() asm volatile("sfence" ::: "memory")
-#endif
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier. All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads. This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies. See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- * CPU 0 CPU 1
- *
- * b = 2;
- * memory_barrier();
- * p = &b; q = p;
- * read_barrier_depends();
- * d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends(). However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- * CPU 0 CPU 1
- *
- * a = 2;
- * memory_barrier();
- * b = 3; y = b;
- * read_barrier_depends();
- * x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b". Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends() do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb() mb()
-#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb() rmb()
-#else
-# define smp_rmb() barrier()
-#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() wmb()
-#else
-# define smp_wmb() barrier()
-#endif
-#define smp_read_barrier_depends() read_barrier_depends()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
-#define smp_mb() barrier()
-#define smp_rmb() barrier()
-#define smp_wmb() barrier()
-#define smp_read_barrier_depends() do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static __always_inline void rdtsc_barrier(void)
-{
- alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
- alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-/*
- * We handle most unaligned accesses in hardware. On the other hand
- * unaligned DMA can be quite expensive on some Nehalem processors.
- *
- * Based on this we disable the IP header alignment in network drivers.
- */
-#define NET_IP_ALIGN 0
-#endif /* _ASM_X86_SYSTEM_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index cfd8144d552..ad6df8ccd71 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -86,7 +86,7 @@ struct thread_info {
#define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */
#define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */
#define TIF_NOTSC 16 /* TSC is not accessible in userland */
-#define TIF_IA32 17 /* 32bit process */
+#define TIF_IA32 17 /* IA32 compatibility process */
#define TIF_FORK 18 /* ret_from_fork */
#define TIF_MEMDIE 20 /* is terminating due to OOM killer */
#define TIF_DEBUG 21 /* uses debug registers */
@@ -95,6 +95,8 @@ struct thread_info {
#define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */
#define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */
#define TIF_SYSCALL_TRACEPOINT 28 /* syscall tracepoint instrumentation */
+#define TIF_ADDR32 29 /* 32-bit address space on 64 bits */
+#define TIF_X32 30 /* 32-bit native x86-64 binary */
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
@@ -116,6 +118,8 @@ struct thread_info {
#define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP)
#define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES)
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_ADDR32 (1 << TIF_ADDR32)
+#define _TIF_X32 (1 << TIF_X32)
/* work to do in syscall_trace_enter() */
#define _TIF_WORK_SYSCALL_ENTRY \
@@ -262,6 +266,18 @@ static inline void set_restore_sigmask(void)
ti->status |= TS_RESTORE_SIGMASK;
set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags);
}
+
+static inline bool is_ia32_task(void)
+{
+#ifdef CONFIG_X86_32
+ return true;
+#endif
+#ifdef CONFIG_IA32_EMULATION
+ if (current_thread_info()->status & TS_COMPAT)
+ return true;
+#endif
+ return false;
+}
#endif /* !__ASSEMBLY__ */
#ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 169be8938b9..c0e108e0807 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -5,7 +5,7 @@
#include <linux/sched.h>
#include <asm/processor.h>
-#include <asm/system.h>
+#include <asm/special_insns.h>
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 0012d0902c5..88eae2aec61 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -89,4 +89,29 @@ asmlinkage void smp_thermal_interrupt(void);
asmlinkage void mce_threshold_interrupt(void);
#endif
+/* Interrupts/Exceptions */
+enum {
+ X86_TRAP_DE = 0, /* 0, Divide-by-zero */
+ X86_TRAP_DB, /* 1, Debug */
+ X86_TRAP_NMI, /* 2, Non-maskable Interrupt */
+ X86_TRAP_BP, /* 3, Breakpoint */
+ X86_TRAP_OF, /* 4, Overflow */
+ X86_TRAP_BR, /* 5, Bound Range Exceeded */
+ X86_TRAP_UD, /* 6, Invalid Opcode */
+ X86_TRAP_NM, /* 7, Device Not Available */
+ X86_TRAP_DF, /* 8, Double Fault */
+ X86_TRAP_OLD_MF, /* 9, Coprocessor Segment Overrun */
+ X86_TRAP_TS, /* 10, Invalid TSS */
+ X86_TRAP_NP, /* 11, Segment Not Present */
+ X86_TRAP_SS, /* 12, Stack Segment Fault */
+ X86_TRAP_GP, /* 13, General Protection Fault */
+ X86_TRAP_PF, /* 14, Page Fault */
+ X86_TRAP_SPURIOUS, /* 15, Spurious Interrupt */
+ X86_TRAP_MF, /* 16, x87 Floating-Point Exception */
+ X86_TRAP_AC, /* 17, Alignment Check */
+ X86_TRAP_MC, /* 18, Machine Check */
+ X86_TRAP_XF, /* 19, SIMD Floating-Point Exception */
+ X86_TRAP_IRET = 32, /* 32, IRET Exception */
+};
+
#endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 15d99153a96..c91e8b9d588 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -61,7 +61,7 @@ extern void check_tsc_sync_source(int cpu);
extern void check_tsc_sync_target(void);
extern int notsc_setup(char *);
-extern void save_sched_clock_state(void);
-extern void restore_sched_clock_state(void);
+extern void tsc_save_sched_clock_state(void);
+extern void tsc_restore_sched_clock_state(void);
#endif /* _ASM_X86_TSC_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8be5f54d936..e0544597cfe 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -557,6 +557,8 @@ struct __large_struct { unsigned long buf[100]; };
extern unsigned long
copy_from_user_nmi(void *to, const void __user *from, unsigned long n);
+extern __must_check long
+strncpy_from_user(char *dst, const char __user *src, long count);
/*
* movsl can be slow when source and dest are not both 8-byte aligned
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 566e803cc60..8084bc73b18 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -213,11 +213,6 @@ static inline unsigned long __must_check copy_from_user(void *to,
return n;
}
-long __must_check strncpy_from_user(char *dst, const char __user *src,
- long count);
-long __must_check __strncpy_from_user(char *dst,
- const char __user *src, long count);
-
/**
* strlen_user: - Get the size of a string in user space.
* @str: The string to measure.
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 1c66d30971a..fcd4b6f3ef0 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -208,10 +208,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
}
}
-__must_check long
-strncpy_from_user(char *dst, const char __user *src, long count);
-__must_check long
-__strncpy_from_user(char *dst, const char __user *src, long count);
__must_check long strnlen_user(const char __user *str, long n);
__must_check long __strnlen_user(const char __user *str, long n);
__must_check long strlen_user(const char __user *str);
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 21f77b89e47..4437001d8e3 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -1,7 +1,17 @@
#ifndef _ASM_X86_UNISTD_H
#define _ASM_X86_UNISTD_H 1
+/* x32 syscall flag bit */
+#define __X32_SYSCALL_BIT 0x40000000
+
#ifdef __KERNEL__
+
+# ifdef CONFIG_X86_X32_ABI
+# define __SYSCALL_MASK (~(__X32_SYSCALL_BIT))
+# else
+# define __SYSCALL_MASK (~0)
+# endif
+
# ifdef CONFIG_X86_32
# include <asm/unistd_32.h>
@@ -14,6 +24,7 @@
# else
# include <asm/unistd_64.h>
+# include <asm/unistd_64_x32.h>
# define __ARCH_WANT_COMPAT_SYS_TIME
# endif
@@ -52,6 +63,8 @@
#else
# ifdef __i386__
# include <asm/unistd_32.h>
+# elif defined(__ILP32__)
+# include <asm/unistd_x32.h>
# else
# include <asm/unistd_64.h>
# endif
diff --git a/arch/x86/include/asm/vga.h b/arch/x86/include/asm/vga.h
index 2723c07835d..44282fbf7bf 100644
--- a/arch/x86/include/asm/vga.h
+++ b/arch/x86/include/asm/vga.h
@@ -17,7 +17,7 @@
#define vga_readb(x) (*(x))
#define vga_writeb(x, y) (*(y) = (x))
-#if CONFIG_FB_EFI
+#ifdef CONFIG_FB_EFI
#define __ARCH_HAS_VGA_DEFAULT_DEVICE
extern struct pci_dev *vga_default_device(void);
extern void vga_set_default_device(struct pci_dev *pdev);
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 815285bcace..8b38be2de9e 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -5,13 +5,8 @@
#include <linux/clocksource.h>
struct vsyscall_gtod_data {
- seqlock_t lock;
+ seqcount_t seq;
- /* open coded 'struct timespec' */
- time_t wall_time_sec;
- u32 wall_time_nsec;
-
- struct timezone sys_tz;
struct { /* extract of a clocksource struct */
int vclock_mode;
cycle_t cycle_last;
@@ -19,8 +14,16 @@ struct vsyscall_gtod_data {
u32 mult;
u32 shift;
} clock;
- struct timespec wall_to_monotonic;
+
+ /* open coded 'struct timespec' */
+ time_t wall_time_sec;
+ u32 wall_time_nsec;
+ u32 monotonic_time_nsec;
+ time_t monotonic_time_sec;
+
+ struct timezone sys_tz;
struct timespec wall_time_coarse;
+ struct timespec monotonic_time_coarse;
};
extern struct vsyscall_gtod_data vsyscall_gtod_data;
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index e0f9aa16358..5da71c27cc5 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -16,7 +16,6 @@
#define _ASM_X86_VIRTEX_H
#include <asm/processor.h>
-#include <asm/system.h>
#include <asm/vmx.h>
#include <asm/svm.h>
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
new file mode 100644
index 00000000000..e58f03b206c
--- /dev/null
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -0,0 +1,79 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+/*
+ * This is largely generic for little-endian machines, but the
+ * optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+ return mask*0x0001020304050608ul >> 56;
+}
+
+#else /* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+ /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+ long a = (0x0ff0001+mask) >> 23;
+ /* Fix the 1 for 00 case */
+ return a & mask;
+}
+
+#endif
+
+#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x))
+
+/* Return the high bit set in the first byte that is a zero */
+static inline unsigned long has_zero(unsigned long a)
+{
+ return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
+}
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+ unsigned long ret, dummy;
+
+ asm(
+ "1:\tmov %2,%0\n"
+ "2:\n"
+ ".section .fixup,\"ax\"\n"
+ "3:\t"
+ "lea %2,%1\n\t"
+ "and %3,%1\n\t"
+ "mov (%1),%0\n\t"
+ "leal %2,%%ecx\n\t"
+ "andl %4,%%ecx\n\t"
+ "shll $3,%%ecx\n\t"
+ "shr %%cl,%0\n\t"
+ "jmp 2b\n"
+ ".previous\n"
+ _ASM_EXTABLE(1b, 3b)
+ :"=&r" (ret),"=&c" (dummy)
+ :"m" (*(unsigned long *)addr),
+ "i" (-sizeof(unsigned long)),
+ "i" (sizeof(unsigned long)-1));
+ return ret;
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h
index 6bf5b8e478c..92e54abf89e 100644
--- a/arch/x86/include/asm/x2apic.h
+++ b/arch/x86/include/asm/x2apic.h
@@ -18,6 +18,11 @@ static const struct cpumask *x2apic_target_cpus(void)
return cpu_online_mask;
}
+static int x2apic_apic_id_valid(int apicid)
+{
+ return 1;
+}
+
static int x2apic_apic_id_registered(void)
{
return 1;
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 3084d634418..764b66a4cf8 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -145,9 +145,11 @@ struct x86_init_ops {
/**
* struct x86_cpuinit_ops - platform specific cpu hotplug setups
* @setup_percpu_clockev: set up the per cpu clock event device
+ * @early_percpu_clock_init: early init of the per cpu clock event device
*/
struct x86_cpuinit_ops {
void (*setup_percpu_clockev)(void);
+ void (*early_percpu_clock_init)(void);
void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node);
};
@@ -160,6 +162,8 @@ struct x86_cpuinit_ops {
* @is_untracked_pat_range exclude from PAT logic
* @nmi_init enable NMI on cpus
* @i8042_detect pre-detect if i8042 controller exists
+ * @save_sched_clock_state: save state for sched_clock() on suspend
+ * @restore_sched_clock_state: restore state for sched_clock() on resume
*/
struct x86_platform_ops {
unsigned long (*calibrate_tsc)(void);
@@ -171,6 +175,8 @@ struct x86_platform_ops {
void (*nmi_init)(void);
unsigned char (*get_nmi_reason)(void);
int (*i8042_detect)(void);
+ void (*save_sched_clock_state)(void);
+ void (*restore_sched_clock_state)(void);
};
struct pci_dev;
@@ -182,18 +188,10 @@ struct x86_msi_ops {
void (*restore_msi_irqs)(struct pci_dev *dev, int irq);
};
-struct x86_ioapic_ops {
- void (*init)(void);
- unsigned int (*read)(unsigned int apic, unsigned int reg);
- void (*write)(unsigned int apic, unsigned int reg, unsigned int value);
- void (*modify)(unsigned int apic, unsigned int reg, unsigned int value);
-};
-
extern struct x86_init_ops x86_init;
extern struct x86_cpuinit_ops x86_cpuinit;
extern struct x86_platform_ops x86_platform;
extern struct x86_msi_ops x86_msi;
-extern struct x86_ioapic_ops x86_ioapic;
extern void x86_init_noop(void);
extern void x86_init_uint_noop(unsigned int unused);
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index a1f2db5f117..cbf0c9d50b9 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -56,6 +56,7 @@ DEFINE_GUEST_HANDLE(int);
DEFINE_GUEST_HANDLE(long);
DEFINE_GUEST_HANDLE(void);
DEFINE_GUEST_HANDLE(uint64_t);
+DEFINE_GUEST_HANDLE(uint32_t);
#endif
#ifndef HYPERVISOR_VIRT_START